Publications |

2026

arXiv

Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability

Licheng Yu, Aiwei Liu, and Songze Li

2026

Bib PDF

@misc{yu2026towardstrongercodewatermarking,
  title = {Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability},
  author = {Yu, Licheng and Liu, Aiwei and Li, Songze},
  year = {2026},
  eprint = {2607.10210},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2607.10210},
}

ACL Findings 2026

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization

Yongtong Gu, Songze Li, and Xia Hu

In Findings of the Association for Computational Linguistics: ACL 2026 , 2026

Bib

@inproceedings{gu2026mashevadingblackbox,
  title = {MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization},
  author = {Gu, Yongtong and Li, Songze and Hu, Xia},
  year = {2026},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  pages = {29749-29769},
}

USENIX Security 2026

When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems

Chenqing Zhu, Yanbo Dai, Yulong Tian, and 2 more authors

In 35th USENIX Security Symposium (USENIX Security 26) , 2026

Bib PDF

@inproceedings{zhu2026whenaggregatorcheatsdata,
  title = {When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems},
  author = {Zhu, Chenqing and Dai, Yanbo and Tian, Yulong and Li, Qingming and Li, Songze},
  year = {2026},
  booktitle = {35th USENIX Security Symposium (USENIX Security 26)},
  eprint = {2606.27511},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2606.27511},
}

arXiv

When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack

Zehan Sun, Dingfan Chen, and Songze Li

2026

Bib PDF

@misc{sun2026whenefficiencybackfirescascading,
  title = {When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack},
  author = {Sun, Zehan and Chen, Dingfan and Li, Songze},
  year = {2026},
  eprint = {2605.17288},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2605.17288},
}

arXiv

Cross-Modal Backdoors in Multimodal Large Language Models

Runhe Wang, Li Bai, Haibo Hu, and 1 more author

2026

Bib PDF

@misc{wang2026crossmodalbackdoorsmultimodal,
  title = {Cross-Modal Backdoors in Multimodal Large Language Models},
  author = {Wang, Runhe and Bai, Li and Hu, Haibo and Li, Songze},
  year = {2026},
  eprint = {2605.07490},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2605.07490},
}

TOSEM 2026

Navigating the risks: A survey of security and privacy threats in LLM-based agents

Yuyou Gan, Yong Yang, Zhe Ma, and 10 more authors

ACM Transactions on Software Engineering and Methodology, 2026

Bib

@article{gan2026navigatingriskssurveysecurity,
  title = {Navigating the risks: A survey of security and privacy threats in LLM-based agents},
  author = {Gan, Yuyou and Yang, Yong and Ma, Zhe and He, Ping and Zeng, Rui and Wang, Yiming and Li, Qingming and Zhou, Chunyi and Li, Songze and Wang, Ting and Gao, Yunjun and Wu, Yingcai and Ji, Shouling},
  year = {2026},
  journal = {ACM Transactions on Software Engineering and Methodology},
}

AAAI 2026

DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew

Zhou Tan, Yirui Huang, Duanshu Fang, and 4 more authors

In Proceedings of the AAAI Conference on Artificial Intelligence , 2026

Bib

@inproceedings{tan2026doblockblockingmaliciousassociation,
  title = {DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew},
  author = {Tan, Zhou and Huang, Yirui and Fang, Duanshu and Yin, Jia-Li and Liu, Xiaolei and Li, Songze and Ji, Shouling},
  year = {2026},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {40},
  pages = {25796-25804},
}

AAAI 2026

Tackling resource-constrained and data-heterogeneity in federated learning with double-weight sparse pack

Qiantao Yang, Liquan Chen, Mingfu Xue, and 1 more author

In Proceedings of the AAAI Conference on Artificial Intelligence , 2026

Bib

@inproceedings{yang2026tacklingresourceconstraineddata,
  title = {Tackling resource-constrained and data-heterogeneity in federated learning with double-weight sparse pack},
  author = {Yang, Qiantao and Chen, Liquan and Xue, Mingfu and Li, Songze},
  year = {2026},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {40},
  pages = {27592-27600},
}

arXiv

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

Lei Ba, Qinbin Li, and Songze Li

2026

Bib PDF

@misc{ba2026cibercomprehensivebenchmarksecurity,
  title = {CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents},
  author = {Ba, Lei and Li, Qinbin and Li, Songze},
  year = {2026},
  eprint = {2602.19547},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2602.19547},
}

arXiv

Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing

Yilong Huang, and Songze Li

2026

Bib PDF

@misc{huang2026beautybeastimperceptibleperturbations,
  title = {Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing},
  author = {Huang, Yilong and Li, Songze},
  year = {2026},
  eprint = {2601.22744},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2601.22744},
}

ACM MM 2026

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise

Puwei Lian, Yujun Cai, Songze Li, and 1 more author

In ACM International Conference on Multimedia (ACM MM) , 2026

Bib PDF

@inproceedings{lian2026noiseasprobemembership,
  title = {Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise},
  author = {Lian, Puwei and Cai, Yujun and Li, Songze and Bao, Bingkun},
  year = {2026},
  booktitle = {ACM International Conference on Multimedia (ACM MM)},
  eprint = {2601.21628},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2601.21628},
}

arXiv

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models

Fengheng Chu, Jiahao Chen, Yuhong Wang, and 4 more authors

2026

Bib PDF

@misc{chu2026attributingexploitingsafetyvectors,
  title = {Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models},
  author = {Chu, Fengheng and Chen, Jiahao and Wang, Yuhong and Wang, Jun and Fu, Zhihui and Ji, Shouling and Li, Songze},
  year = {2026},
  eprint = {2601.15801},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2601.15801},
}

TDSC 2026

Sleight: Hidden Data Privacy Breaches in Federated Learning

Xueluan Gong, Yuji Wang, Shuike Li, and 5 more authors

IEEE Transactions on Dependable and Secure Computing, 2026

Bib

@article{gong2026sleighthiddendataprivacy,
  title = {Sleight: Hidden Data Privacy Breaches in Federated Learning},
  author = {Gong, Xueluan and Wang, Yuji and Li, Shuike and Sun, Mengyuan and Li, Songze and Chen, Chen and Wang, Qian and Lam, Kwok-Yan},
  year = {2026},
  journal = {IEEE Transactions on Dependable and Secure Computing},
}

arXiv

CODE: A Contradiction-Based Deliberation Extension Framework for Overthinking Attacks on Retrieval-Augmented Generation

Xiaolei Zhang, Xiaojun Jia, Liquan Chen, and 1 more author

2026

Bib PDF

@misc{zhang2026codecontradictionbaseddeliberation,
  title = {CODE: A Contradiction-Based Deliberation Extension Framework for Overthinking Attacks on Retrieval-Augmented Generation},
  author = {Zhang, Xiaolei and Jia, Xiaojun and Chen, Liquan and Li, Songze},
  year = {2026},
  eprint = {2601.13112},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2601.13112},
}

arXiv

Knowledge-driven multi-turn jailbreaking on large language models

Songze Li, Ruishi He, Xiaojun Jia, and 2 more authors

2026

Bib PDF

@misc{li2026knowledgedrivenmultiturn,
  title = {Knowledge-driven multi-turn jailbreaking on large language models},
  author = {Li, Songze and He, Ruishi and Jia, Xiaojun and Wang, Jun and Fu, Zhihui},
  year = {2026},
  eprint = {2601.05445},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2601.05445},
}

Globecom 2026

Coded Computing: A Transformative Framework for Edge Computing

Songze Li, and A Salman Avestimehr

Global Communications, 2026

Bib

@article{li2026codedcomputingtransformativeframework,
  title = {Coded Computing: A Transformative Framework for Edge Computing},
  author = {Li, Songze and Avestimehr, A Salman},
  year = {2026},
  journal = {Global Communications},
  volume = {2026},
}

NDSS 2026

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography

Songze Li, Jiameng Cheng, Yiming Li, and 2 more authors

In Network and Distributed System Security Symposium (NDSS) , 2026

Bib HTML PDF

@inproceedings{li2025odysseusjailbreakingcommercialmultimodal,
  title = {Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography},
  author = {Li, Songze and Cheng, Jiameng and Li, Yiming and Jia, Xiaojun and Tao, Dacheng},
  year = {2026},
  booktitle = {Network and Distributed System Security Symposium (NDSS)},
  eprint = {2512.20168},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2512.20168},
}

ICML 2026

Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective

Puwei Lian, Yujun Cai, Songze Li, and 1 more author

In International Conference on Machine Learning (ICML) , 2026

Bib HTML PDF

@inproceedings{lian2025enhancingmembershipinferenceattacks,
  title = {Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective},
  author = {Lian, Puwei and Cai, Yujun and Li, Songze and Bao, Bingkun},
  year = {2026},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2505.20955},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2505.20955},
}

2025

arXiv

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models

Hao Chen, Yiwei Wang, and Songze Li

2025

Bib PDF

@misc{chen2025bierasingbidirectionalframework,
  title = {Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models},
  author = {Chen, Hao and Wang, Yiwei and Li, Songze},
  year = {2025},
  eprint = {2512.13039},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2512.13039},
}

arXiv

Funcpoison: Poisoning function library to hijack multi-agent autonomous driving systems

Yuzhen Long, and Songze Li

2025

Bib PDF

@misc{long2025funcpoisonpoisoningfunctionlibrary,
  title = {Funcpoison: Poisoning function library to hijack multi-agent autonomous driving systems},
  author = {Long, Yuzhen and Li, Songze},
  year = {2025},
  eprint = {2509.24408},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2509.24408},
}

arXiv

Visual CoT Makes VLMs Smarter but More Fragile

Chunxue Xu, Yiwei Wang, Yujun Cai, and 2 more authors

2025

Bib PDF

@misc{xu2025visualcotmakesvlms,
  title = {Visual CoT Makes VLMs Smarter but More Fragile},
  author = {Xu, Chunxue and Wang, Yiwei and Cai, Yujun and Hooi, Bryan and Li, Songze},
  year = {2025},
  eprint = {2509.23789},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2509.23789},
}

arXiv

Responsible diffusion: A comprehensive survey on safety, ethics, and trust in diffusion models

Kang Wei, Xin Yuan, Fushuo Huo, and 5 more authors

2025

Bib PDF

@misc{wei2025responsiblediffusioncomprehensivesurvey,
  title = {Responsible diffusion: A comprehensive survey on safety, ethics, and trust in diffusion models},
  author = {Wei, Kang and Yuan, Xin and Huo, Fushuo and Ma, Chuan and Yuan, Long and Li, Songze and Ding, Ming and Tao, Dacheng},
  year = {2025},
  eprint = {2509.22723},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2509.22723},
}

ICANN 2025

MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models

Jin Xie, Danny HK Tsang, and Songze Li

In International Conference on Artificial Neural Networks (ICANN) , 2025

Bib

@inproceedings{xie2025msfusiondynamicmodelsplitting,
  title = {MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models},
  author = {Xie, Jin and Tsang, Danny HK and Li, Songze},
  year = {2025},
  booktitle = {International Conference on Artificial Neural Networks (ICANN)},
  pages = {13-25},
}

CASE 2025

Federated Learning for Deep Anomaly Detection with Noisy and Heterogeneous Data

Ao Li, Songze Li, and Fugee Tsung

In 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE) , 2025

Bib

@inproceedings{li2025federatedlearningdeepanomaly,
  title = {Federated Learning for Deep Anomaly Detection with Noisy and Heterogeneous Data},
  author = {Li, Ao and Li, Songze and Tsung, Fugee},
  year = {2025},
  booktitle = {2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)},
  pages = {250-255},
}

CRYPTO 2025

Resolving the efficiency-utility dilemma of threshold linearly homomorphic encryption via message-space adapter

Yijia Chang, Rongmao Chen, Chao Lin, and 2 more authors

In Annual International Cryptology Conference (CRYPTO) , 2025

Bib

@inproceedings{chang2025resolvingefficiencyutilitydilemma,
  title = {Resolving the efficiency-utility dilemma of threshold linearly homomorphic encryption via message-space adapter},
  author = {Chang, Yijia and Chen, Rongmao and Lin, Chao and Li, Songze and Huang, Xinyi},
  year = {2025},
  booktitle = {Annual International Cryptology Conference (CRYPTO)},
  pages = {269-303},
}

IWQoS 2025

SecurePay: Enabling secure and fast payment processing for platform economy

Junru Lin, Mingzhe Liu, Songze Li, and 1 more author

In 2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS) , 2025

Bib

@inproceedings{lin2025securepayenablingsecurefast,
  title = {SecurePay: Enabling secure and fast payment processing for platform economy},
  author = {Lin, Junru and Liu, Mingzhe and Li, Songze and Wang, Xuechao},
  year = {2025},
  booktitle = {2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)},
  pages = {1-6},
}

arXiv

Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers

Zhenhao Huang, Kai Liang, Yuanming Shi, and 2 more authors

2025

Bib PDF

@misc{huang2025asymptoticallyoptimalsecureaggregation,
  title = {Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers},
  author = {Huang, Zhenhao and Liang, Kai and Shi, Yuanming and Li, Songze and Wu, Youlong},
  year = {2025},
  eprint = {2506.23680},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2506.23680},
}

TIFS 2025

Secure Embedding Aggregation for Cross-Silo Federated Representation Learning

Songze Li, Jiaxiang Tang, Jinbao Zhu, and 3 more authors

IEEE Transactions on Information Forensics and Security, 2025

Bib

@article{li2025secureembeddingaggregationcross,
  title = {Secure Embedding Aggregation for Cross-Silo Federated Representation Learning},
  author = {Li, Songze and Tang, Jiaxiang and Zhu, Jinbao and Zhang, Kai and Sun, Lichao and Dong, Changyu},
  year = {2025},
  journal = {IEEE Transactions on Information Forensics and Security},
  volume = {20},
  pages = {6810-6825},
}

arXiv

TooBadRL: Trigger optimization to boost effectiveness of backdoor attacks on deep reinforcement learning

Mingxuan Zhang, Oubo Ma, Kang Wei, and 2 more authors

2025

Bib PDF

@misc{zhang2025toobadrltriggeroptimizationboost,
  title = {TooBadRL: Trigger optimization to boost effectiveness of backdoor attacks on deep reinforcement learning},
  author = {Zhang, Mingxuan and Ma, Oubo and Wei, Kang and Li, Songze and Ji, Shouling},
  year = {2025},
  eprint = {2506.09562},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2506.09562},
}

arXiv

Llms cannot reliably judge (yet?): A comprehensive assessment on the robustness of llm-as-a-judge

Songze Li, Chuokun Xu, Jiaying Wang, and 6 more authors

2025

Bib PDF

@misc{li2025llmscannotreliablyjudge,
  title = {Llms cannot reliably judge (yet?): A comprehensive assessment on the robustness of llm-as-a-judge},
  author = {Li, Songze and Xu, Chuokun and Wang, Jiaying and Gong, Xueluan and Chen, Chen and Zhang, Jirui and Wang, Jun and Lam, Kwok-Yan and Ji, Shouling},
  year = {2025},
  eprint = {2506.09443},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2506.09443},
}

CVPR 2025

Dede: Detecting backdoor samples for ssl encoders via decoders

Sizai Hou, Songze Li, and Duanyi Yao

In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2025

Bib

@inproceedings{hou2025dededetectingbackdoorsamples,
  title = {Dede: Detecting backdoor samples for ssl encoders via decoders},
  author = {Hou, Sizai and Li, Songze and Yao, Duanyi},
  year = {2025},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {20675-20684},
}

TIFS 2025

PriRoAgg: Achieving robust model aggregation with minimum privacy leakage for federated learning

Sizai Hou, Songze Li, Tayyebeh Jahani-Nezhad, and 1 more author

IEEE Transactions on Information Forensics and Security, 2025

Bib

@article{hou2025priroaggachievingrobustmodel,
  title = {PriRoAgg: Achieving robust model aggregation with minimum privacy leakage for federated learning},
  author = {Hou, Sizai and Li, Songze and Jahani-Nezhad, Tayyebeh and Caire, Giuseppe},
  year = {2025},
  journal = {IEEE Transactions on Information Forensics and Security},
  volume = {20},
  pages = {5690-5704},
}

arXiv

Privacy-preserving prompt personalization in federated learning for multimodal large language models

Sizai Hou, Songze Li, and Baturalp Buyukates

2025

Bib PDF

@misc{hou2025privacypreservingpromptpersonalization,
  title = {Privacy-preserving prompt personalization in federated learning for multimodal large language models},
  author = {Hou, Sizai and Li, Songze and Buyukates, Baturalp},
  year = {2025},
  eprint = {2505.22447},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2505.22447},
}

ICLR 2025

Agent-oriented planning in multi-agent systems

Ao Li, Yuexiang Xie, Songze Li, and 3 more authors

In International Conference on Learning Representations (ICLR) , 2025

Bib

@inproceedings{li2025agentorientedplanningmulti,
  title = {Agent-oriented planning in multi-agent systems},
  author = {Li, Ao and Xie, Yuexiang and Li, Songze and Tsung, Fugee and Ding, Bolin and Li, Yaliang},
  year = {2025},
  booktitle = {International Conference on Learning Representations (ICLR)},
  pages = {19495-19517},
}

arXiv

ReCIT: Reconstructing full private data from gradient in parameter-efficient fine-tuning of large language models

Jin Xie, Ruishi He, Songze Li, and 2 more authors

2025

Bib PDF

@misc{xie2025recitreconstructingfullprivate,
  title = {ReCIT: Reconstructing full private data from gradient in parameter-efficient fine-tuning of large language models},
  author = {Xie, Jin and He, Ruishi and Li, Songze and Jia, Xiaojun and Ji, Shouling},
  year = {2025},
  eprint = {2504.20570},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2504.20570},
}

arXiv

TrojanDam: Detection-free backdoor defense in federated learning through proactive model robustification utilizing OOD data

Yanbo Dai, Songze Li, Zihan Gan, and 1 more author

2025

Bib PDF

@misc{dai2025trojandamdetectionfreebackdoor,
  title = {TrojanDam: Detection-free backdoor defense in federated learning through proactive model robustification utilizing OOD data},
  author = {Dai, Yanbo and Li, Songze and Gan, Zihan and Gong, Xueluan},
  year = {2025},
  eprint = {2504.15674},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2504.15674},
}

PrivateNLP 2025

Tuni: A textual unimodal detector for identity inference in clip models

Songze Li, Ruoxi Cheng, and Xiaojun Jia

In Proceedings of the Sixth Workshop on Privacy in Natural Language Processing , 2025

Bib

@inproceedings{li2025tunitextualunimodaldetector,
  title = {Tuni: A textual unimodal detector for identity inference in clip models},
  author = {Li, Songze and Cheng, Ruoxi and Jia, Xiaojun},
  year = {2025},
  booktitle = {Proceedings of the Sixth Workshop on Privacy in Natural Language Processing},
  pages = {1-13},
}

COLM 2025

How does Watermarking Affect Visual Language Models in Document Understanding?

Chunxue Xu, Yiwei Wang, Bryan Hooi, and 2 more authors

In Conference on Language Modeling (COLM) , 2025

Bib PDF

@inproceedings{xu2025howdoeswatermarkingaffect,
  title = {How does Watermarking Affect Visual Language Models in Document Understanding?},
  author = {Xu, Chunxue and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Li, Songze},
  year = {2025},
  booktitle = {Conference on Language Modeling (COLM)},
  eprint = {2504.01048},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2504.01048},
}

arXiv

When data manipulation meets attack goals: An in-depth survey of attacks for vlms

Aobotao Dai, Xinyu Ma, Lei Chen, and 2 more authors

2025

Bib PDF

@misc{dai2025whendatamanipulationmeets,
  title = {When data manipulation meets attack goals: An in-depth survey of attacks for vlms},
  author = {Dai, Aobotao and Ma, Xinyu and Chen, Lei and Li, Songze and Wang, Lin},
  year = {2025},
  eprint = {2502.06390},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2502.06390},
}

USENIX Security 2025

Arbitrary-Threshold Fully Homomorphic Encryption with Lower Complexity

Yijia Chang, and Songze Li

In 34th USENIX Security Symposium (USENIX Security 25) , 2025

Bib

@inproceedings{chang2025arbitrarythresholdfullyhomomorphic,
  title = {{Arbitrary-Threshold} Fully Homomorphic Encryption with Lower Complexity},
  author = {Chang, Yijia and Li, Songze},
  year = {2025},
  booktitle = {34th USENIX Security Symposium (USENIX Security 25)},
  pages = {8403-8422},
}

2024

TIFS 2024

Privacy-preserving coded schemes for multi-server federated learning with straggling links

Kai Liang, Songze Li, Ming Ding, and 2 more authors

IEEE Transactions on Information Forensics and Security, 2024

Bib

@article{liang2024privacypreservingcodedschemes,
  title = {Privacy-preserving coded schemes for multi-server federated learning with straggling links},
  author = {Liang, Kai and Li, Songze and Ding, Ming and Tian, Feng and Wu, Youlong},
  year = {2024},
  journal = {IEEE Transactions on Information Forensics and Security},
  volume = {20},
  pages = {1222-1236},
}

NDSS 2025

URVFL: Undetectable data reconstruction attack on vertical federated learning

Duanyi Yao, Songze Li, Xueluan Gong, and 2 more authors

In The Network and Distributed System Security (NDSS) 2025 , 2024

Bib

@inproceedings{yao2024urvflundetectabledatareconstruction,
  title = {URVFL: Undetectable data reconstruction attack on vertical federated learning},
  author = {Yao, Duanyi and Li, Songze and Gong, Xueluan and Hou, Sizai and Pan, Gaoning},
  year = {2024},
  booktitle = {The Network and Distributed System Security (NDSS) 2025},
}

NDSS 2025

Manifoldchain: Maximizing Blockchain Throughput via Bandwidth-Clustered Sharding

Chunjiang Che, Songze Li, and Xuechao Wang

2024

Bib PDF

@misc{che2024manifoldchainmaximizingblockchainthroughput,
  title = {Manifoldchain: Maximizing Blockchain Throughput via Bandwidth-Clustered Sharding},
  author = {Che, Chunjiang and Li, Songze and Wang, Xuechao},
  year = {2024},
  eprint = {2407.16295},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2407.16295},
}

TWC 2024

Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design

Yuchang Sun, Jiawei Shao, Yuyi Mao, and 2 more authors

IEEE Transactions on Wireless Communications, 2024

Bib PDF

@article{10336724,
  author = {Sun, Yuchang and Shao, Jiawei and Mao, Yuyi and Li, Songze and Zhang, Jun},
  journal = {IEEE Transactions on Wireless Communications},
  title = {Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design},
  year = {2024},
  volume = {23},
  number = {6},
  pages = {6623-6638},
  keywords = {Servers;Training;Computational modeling;Performance evaluation;Data privacy;Data models;Noise level;Federated learning (FL);coded computing;straggler effect;mutual information differential privacy (MI-DP);incentive mechanism},
  doi = {10.1109/TWC.2023.3334732},
}

ICLR 2024

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit

Duanyi YAO, Songze Li, Ye XUE, and 1 more author

In The Twelfth International Conference on Learning Representations , 2024

Bib PDF

@inproceedings{yao2024constructing,
  title = {Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit},
  author = {YAO, Duanyi and Li, Songze and XUE, Ye and Liu, Jin},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=m52uU0dVbH},
}

USENIX Security 2024

BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning

Songze Li, and Yanbo Dai

CoRR, 2024

Bib PDF

@article{DBLP:journals/corr/abs-2405-20862,
  author = {Li, Songze and Dai, Yanbo},
  title = {BackdoorIndicator: Leveraging {OOD} Data for Proactive Backdoor Detection
                    in Federated Learning},
  journal = {CoRR},
  volume = {abs/2405.20862},
  year = {2024},
  url = {https://doi.org/10.48550/arXiv.2405.20862},
  doi = {10.48550/ARXIV.2405.20862},
  eprinttype = {arXiv},
  eprint = {2405.20862},
  timestamp = {Mon, 24 Jun 2024 10:16:41 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2405-20862.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

arXiv

Towards Client Driven Federated Learning

Songze Li, and Chenqing Zhu

CoRR, 2024

Bib PDF

@article{DBLP:journals/corr/abs-2405-15407,
  author = {Li, Songze and Zhu, Chenqing},
  title = {Towards Client Driven Federated Learning},
  journal = {CoRR},
  volume = {abs/2405.15407},
  year = {2024},
  url = {https://doi.org/10.48550/arXiv.2405.15407},
  doi = {10.48550/ARXIV.2405.15407},
  eprinttype = {arXiv},
  eprint = {2405.15407},
  timestamp = {Wed, 19 Jun 2024 08:52:55 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2405-15407.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

arXiv

Identity Inference from CLIP Models using Only Textual Data

Songze Li, Ruoxi Cheng, and Xiaojun Jia

CoRR, 2024

Bib PDF

@article{DBLP:journals/corr/abs-2405-14517,
  author = {Li, Songze and Cheng, Ruoxi and Jia, Xiaojun},
  title = {Identity Inference from {CLIP} Models using Only Textual Data},
  journal = {CoRR},
  volume = {abs/2405.14517},
  year = {2024},
  url = {https://doi.org/10.48550/arXiv.2405.14517},
  doi = {10.48550/ARXIV.2405.14517},
  eprinttype = {arXiv},
  eprint = {2405.14517},
  timestamp = {Wed, 19 Jun 2024 08:52:51 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2405-14517.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

arXiv

Leveraging Label Information for Stealthy Data Stealing in Vertical Federated Learning

Duanyi Yao, Songze Li, Xueluan Gong, and 2 more authors

CoRR, 2024

Bib PDF

@article{DBLP:journals/corr/abs-2404-19582,
  author = {Yao, Duanyi and Li, Songze and Gong, Xueluan and Hou, Sizai and Pan, Gaoning},
  title = {Leveraging Label Information for Stealthy Data Stealing in Vertical
                    Federated Learning},
  journal = {CoRR},
  volume = {abs/2404.19582},
  year = {2024},
  url = {https://doi.org/10.48550/arXiv.2404.19582},
  doi = {10.48550/ARXIV.2404.19582},
  eprinttype = {arXiv},
  eprint = {2404.19582},
  timestamp = {Mon, 27 May 2024 14:55:45 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2404-19582.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

arXiv

FedMeS: Personalized Federated Continual Learning Leveraging Local Memory

Jin Xie, Chenqing Zhu, and Songze Li

CoRR, 2024

Bib PDF

@article{DBLP:journals/corr/abs-2404-12710,
  author = {Xie, Jin and Zhu, Chenqing and Li, Songze},
  title = {FedMeS: Personalized Federated Continual Learning Leveraging Local
                    Memory},
  journal = {CoRR},
  volume = {abs/2404.12710},
  year = {2024},
  url = {https://doi.org/10.48550/arXiv.2404.12710},
  doi = {10.48550/ARXIV.2404.12710},
  eprinttype = {arXiv},
  eprint = {2404.12710},
  timestamp = {Wed, 22 May 2024 08:50:15 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2404-12710.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

arXiv

OmniLytics+: A Secure, Efficient, and Affordable Blockchain Data Market for Machine Learning through Off-Chain Processing

Songze Li, Mingzhe Liu, and Mengqi Chen

2024

Bib PDF

@misc{li2024omnilyticssecureefficientaffordable,
  title = {OmniLytics+: A Secure, Efficient, and Affordable Blockchain Data Market for Machine Learning through Off-Chain Processing},
  author = {Li, Songze and Liu, Mingzhe and Chen, Mengqi},
  year = {2024},
  eprint = {2406.06477},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2406.06477},
}

TCOM 2024

On Exploiting Network Topology for Hierarchical Coded Multi-task Learning

Haoyang Hu, Songze Li, Minquan Cheng, and 3 more authors

IEEE Transactions on Communications, 2024

Bib

@article{10478954,
  author = {Hu, Haoyang and Li, Songze and Cheng, Minquan and Ma, Shuai and Shi, Yuanming and Wu, Youlong},
  journal = {IEEE Transactions on Communications},
  title = {On Exploiting Network Topology for Hierarchical Coded Multi-task Learning},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-1},
  keywords = {Relays;Servers;Task analysis;Distance learning;Computer aided instruction;Downlink;Uplink;Multi-task learning;coding techniques;distributed learning;hierarchical systems;communication load},
  doi = {10.1109/TCOMM.2024.3381671},
}

2023

JSAC 2023

SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning

Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li, and 1 more author

IEEE Journal on Selected Areas in Communications, 2023

Bib PDF

@article{10058697,
  author = {Jahani-Nezhad, Tayyebeh and Maddah-Ali, Mohammad Ali and Li, Songze and Caire, Giuseppe},
  journal = {IEEE Journal on Selected Areas in Communications},
  title = {SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning},
  year = {2023},
  volume = {41},
  number = {4},
  pages = {977-989},
  keywords = {Servers;Load modeling;Computational modeling;Cryptography;Data models;Symbols;Protocols;Federated learning;secure aggregation;secret sharing;dropout resiliency;optimal communication load},
  doi = {10.1109/JSAC.2023.3242702},
}

ICML 2023
Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning

Yanbo Dai, and Songze Li

In Proceedings of the 40th International Conference on Machine Learning , 2023

Abs Bib PDF

In a federated learning (FL) system, distributed clients upload their local models to a central server to aggregate into a global model. Malicious clients may plant backdoors into the global model through uploading poisoned local models, causing images with specific patterns to be misclassified into some target labels. Backdoors planted by current attacks are not durable, and vanish quickly once the attackers stop model poisoning. In this paper, we investigate the connection between the durability of FL backdoors and the relationships between benign images and poisoned images (i.e., the images whose labels are flipped to the target label during local training). Specifically, benign images with the original and the target labels of the poisoned images are found to have key effects on backdoor durability. Consequently, we propose a novel attack, Chameleon, which utilizes contrastive learning to further amplify such effects towards a more durable backdoor. Extensive experiments demonstrate that Chameleon significantly extends the backdoor lifespan over baselines by 1.2\times ∼4\times, for a wide range of image datasets, backdoor types, and model architectures.
@inproceedings{pmlr-v202-dai23a, title = {Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning}, author = {Dai, Yanbo and Li, Songze}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {6712--6725}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v202/dai23a.html}, }
ICML 2023
FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

Songze Li, Duanyi Yao, and Jin Liu

In Proceedings of the 40th International Conference on Machine Learning , 2023

Abs Bib PDF

In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features are privately stored on different clients. The problem of split VFL is to train a model split between the server and the clients. This paper aims to address two major challenges in split VFL: 1) performance degradation due to straggling clients during training; and 2) data and model privacy leakage from clients’ uploaded data embeddings. We propose FedVS to simultaneously address these two challenges. The key idea of FedVS is to design secret sharing schemes for the local data and models, such that information-theoretical privacy against colluding clients and curious server is guaranteed, and the aggregation of all clients’ embeddings is reconstructed losslessly, via decrypting computation shares from the non-straggling clients. Extensive experiments on various types of VFL datasets (including tabular, CV, and multi-view) demonstrate the universal advantages of FedVS in straggler mitigation and privacy protection over baseline protocols.
@inproceedings{pmlr-v202-li23an, title = {{F}ed{VS}: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models}, author = {Li, Songze and Yao, Duanyi and Liu, Jin}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {20296--20311}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v202/li23an.html}, }

TIFS 2023

Information-Theoretically Private Matrix Multiplication From MDS-Coded Storage

Jinbao Zhu, Songze Li, and Jie Li

IEEE Transactions on Information Forensics and Security, 2023

Bib PDF

@article{10054080,
  author = {Zhu, Jinbao and Li, Songze and Li, Jie},
  journal = {IEEE Transactions on Information Forensics and Security},
  title = {Information-Theoretically Private Matrix Multiplication From MDS-Coded Storage},
  year = {2023},
  volume = {18},
  number = {},
  pages = {1680-1695},
  keywords = {Servers;Privacy;Cryptography;Diseases;Hospitals;Computational modeling;Codes;Distributed matrix multiplication;data and index privacy;MDS-coded storage;colluding servers;polynomial secret sharing},
  doi = {10.1109/TIFS.2023.3249565},
}

TCOM 2023

Communication-Efficient Coded Computing for Distributed Multi-Task Learning

Haoyang Hu, Youlong Wu, Yuanming Shi, and 3 more authors

IEEE Transactions on Communications, 2023

Bib

@article{10123015,
  author = {Hu, Haoyang and Wu, Youlong and Shi, Yuanming and Li, Songze and Jiang, Chunxiao and Zhang, Wei},
  journal = {IEEE Transactions on Communications},
  title = {Communication-Efficient Coded Computing for Distributed Multi-Task Learning},
  year = {2023},
  volume = {71},
  number = {7},
  pages = {3861-3875},
  keywords = {Uplink;Downlink;Servers;Task analysis;Encoding;Distributed databases;Computational modeling;Multi-task learning;coding;distributed learning;communication load},
  doi = {10.1109/TCOMM.2023.3275194},
}

ITW 2023

Coded Distributed Computing for Hierarchical Multi-task Learning

Haoyang Hu, Songze Li, Minquan Cheng, and 1 more author

In 2023 IEEE Information Theory Workshop (ITW) , 2023

Bib PDF

@inproceedings{10161632,
  author = {Hu, Haoyang and Li, Songze and Cheng, Minquan and Wu, Youlong},
  booktitle = {2023 IEEE Information Theory Workshop (ITW)},
  title = {Coded Distributed Computing for Hierarchical Multi-task Learning},
  year = {2023},
  volume = {},
  number = {},
  pages = {480-485},
  keywords = {Learning systems;Upper bound;Multitasking;Downlink;Topology;Servers;Relays;Multi-task learning;coded computing;distributed learning;hierarchical systems;communication load},
  doi = {10.1109/ITW55543.2023.10161632},
}

arXiv

Generalized Lagrange Coded Computing: A Flexible Computation-Communication Tradeoff for Resilient, Secure, and Private Computation

Jinbao Zhu, Hengxuan Tang, Songze Li, and 1 more author

2023

Bib PDF

@misc{zhu2023generalizedlagrangecodedcomputing,
  title = {Generalized Lagrange Coded Computing: A Flexible Computation-Communication Tradeoff for Resilient, Secure, and Private Computation},
  author = {Zhu, Jinbao and Tang, Hengxuan and Li, Songze and Chang, Yijia},
  year = {2023},
  eprint = {2204.11168},
  archiveprefix = {arXiv},
  primaryclass = {cs.IT},
  url = {https://arxiv.org/abs/2204.11168},
}

NeurIPS Workshop
Active Few-shot Learning For RouteNet-Fermi

Xiaoyi Fu, Menghan Shao, Songze Li, and 1 more author

In Proceedings of the 2nd on Graph Neural Networking Workshop 2023 , Paris, France, 2023

Abs Bib

Machine-learning-based Network Modeling requires a compact training data set that contains diversified network topology and configurations covering different congestion levels. We formalize the problem of modeling network delay using Multi-stage Message Passing Graph Neural Networks (GNNs) under the constraints of a limited number of training samples and a limited number of nodes for the topology of each sample as a few-shot learning problem. To tackle it, we propose an active learning algorithm that selectively randomizes initial features that are invariant of node numbers and then uses pool-based uncertainty sampling for selecting the approximated optimal network topology based on the Shannon entropy. The approximation could be theoretically proven and confirmed with experimental results.
@inproceedings{10.1145/3630049.3630174, author = {Fu, Xiaoyi and Shao, Menghan and Li, Songze and Yang, Liuqing}, title = {Active Few-shot Learning For RouteNet-Fermi}, year = {2023}, isbn = {9798400704482}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3630049.3630174}, doi = {10.1145/3630049.3630174}, booktitle = {Proceedings of the 2nd on Graph Neural Networking Workshop 2023}, pages = {19–24}, numpages = {6}, keywords = {active learning, few-shot learning, graph neural networks}, location = {Paris, France}, series = {GNNet '23}, }

GLOBECOM 2023

Multi-Server Secure Aggregation with Unreliable Communication Links

Kai Liang, Songze Li, Ming Ding, and 1 more author

In GLOBECOM 2023 - 2023 IEEE Global Communications Conference , 2023

Bib PDF

@inproceedings{10437745,
  author = {Liang, Kai and Li, Songze and Ding, Ming and Wu, Youlong},
  booktitle = {GLOBECOM 2023 - 2023 IEEE Global Communications Conference},
  title = {Multi-Server Secure Aggregation with Unreliable Communication Links},
  year = {2023},
  volume = {},
  number = {},
  pages = {2560-2565},
  keywords = {Threat modeling;Training;Redundancy;Downlink;Security;Channel coding;Uplink;Coding computing;federated learning;straggling links;secure aggregation},
  doi = {10.1109/GLOBECOM54140.2023.10437745},
}

ISIT 2023

Secure Gradient Aggregation for Wireless Multi-Server Federated Learning

Zhenhao Huang, Songze Li, Kai Liang, and 1 more author

In 2023 IEEE International Symposium on Information Theory (ISIT) , 2023

Bib

@inproceedings{10206522,
  author = {Huang, Zhenhao and Li, Songze and Liang, Kai and Wu, Youlong},
  booktitle = {2023 IEEE International Symposium on Information Theory (ISIT)},
  title = {Secure Gradient Aggregation for Wireless Multi-Server Federated Learning},
  year = {2023},
  volume = {},
  number = {},
  pages = {2404-2409},
  keywords = {Wireless communication;Wireless sensor networks;Federated learning;Downlink;Encoding;Servers;Communication system security},
  doi = {10.1109/ISIT54713.2023.10206522},
}

ISIT 2023

Secure Embedding Aggregation for Federated Representation Learning

Jiaxiang Tang, Jinbao Zhu, Songze Li, and 1 more author

In 2023 IEEE International Symposium on Information Theory (ISIT) , 2023

Bib PDF

@inproceedings{10206974,
  author = {Tang, Jiaxiang and Zhu, Jinbao and Li, Songze and Sun, Lichao},
  booktitle = {2023 IEEE International Symposium on Information Theory (ISIT)},
  title = {Secure Embedding Aggregation for Federated Representation Learning},
  year = {2023},
  volume = {},
  number = {},
  pages = {2392-2397},
  keywords = {Representation learning;Privacy;Protocols;Social networking (online);Distributed databases;Complexity theory;Servers},
  doi = {10.1109/ISIT54713.2023.10206974},
}

2022

MLSys 2022

LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning

Jinhyun So, Chaoyang He, Chien-Sheng Yang, and 5 more authors

In Proceedings of Machine Learning and Systems , 2022

Bib PDF

@inproceedings{MLSYS2022_6c44dc73,
  author = {So, Jinhyun and He, Chaoyang and Yang, Chien-Sheng and Li, Songze and Yu, Qian and E. Ali, Ramy and Guler, Basak and Avestimehr, Salman},
  booktitle = {Proceedings of Machine Learning and Systems},
  editor = {Marculescu, D. and Chi, Y. and Wu, C.},
  pages = {694--720},
  title = {LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning},
  url = {https://proceedings.mlsys.org/paper_files/paper/2022/file/6c44dc73014d66ba49b28d483a8f8b0d-Paper.pdf},
  volume = {4},
  year = {2022},
}

NeurIPS 2022

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing

Jiawei Shao, Yuchang Sun, Songze Li, and 1 more author

In Advances in Neural Information Processing Systems , 2022

Bib PDF

@inproceedings{NEURIPS2022_448fc91f,
  author = {Shao, Jiawei and Sun, Yuchang and Li, Songze and Zhang, Jun},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.},
  pages = {10533--10545},
  publisher = {Curran Associates, Inc.},
  title = {DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/448fc91f669c15d10364ee01d512cc10-Paper-Conference.pdf},
  volume = {35},
  year = {2022},
}

ISIT 2022

SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees

Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li, and 1 more author

In 2022 IEEE International Symposium on Information Theory (ISIT) , 2022

Bib PDF

@inproceedings{9834750,
  author = {Jahani-Nezhad, Tayyebeh and Maddah-Ali, Mohammad Ali and Li, Songze and Caire, Giuseppe},
  booktitle = {2022 IEEE International Symposium on Information Theory (ISIT)},
  title = {SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees},
  year = {2022},
  volume = {},
  number = {},
  pages = {103-108},
  keywords = {Protocols;Distributed databases;Collaborative work;Data models;Servers;Cryptography;Communication networks;Federated learning;Communication-efficient secure aggregation;Secret sharing;Dropout resiliency},
  doi = {10.1109/ISIT50566.2022.9834750},
  bibtex_show = true,
}

ISIT 2022

Stochastic Coded Federated Learning with Convergence and Privacy Guarantees

Yuchang Sun, Jiawei Shao, Songze Li, and 2 more authors

In 2022 IEEE International Symposium on Information Theory (ISIT) , 2022

Bib PDF

@inproceedings{9834445,
  author = {Sun, Yuchang and Shao, Jiawei and Li, Songze and Mao, Yuyi and Zhang, Jun},
  booktitle = {2022 IEEE International Symposium on Information Theory (ISIT)},
  title = {Stochastic Coded Federated Learning with Convergence and Privacy Guarantees},
  year = {2022},
  volume = {},
  number = {},
  pages = {2028-2033},
  keywords = {Training;Privacy;Differential privacy;Computational modeling;Stochastic processes;Machine learning;Collaborative work;Federated learning (FL);coded computing;stochastic gradient descent (SGD);mutual information differential privacy (MI-DP)},
  doi = {10.1109/ISIT50566.2022.9834445},
}

TIT 2022

Symmetric Private Polynomial Computation From Lagrange Encoding

Jinbao Zhu, Qifa Yan, Xiaohu Tang, and 1 more author

IEEE Transactions on Information Theory, 2022

Bib PDF

@article{9672125,
  author = {Zhu, Jinbao and Yan, Qifa and Tang, Xiaohu and Li, Songze},
  journal = {IEEE Transactions on Information Theory},
  title = {Symmetric Private Polynomial Computation From Lagrange Encoding},
  year = {2022},
  volume = {68},
  number = {4},
  pages = {2704-2718},
  keywords = {Servers;Systematics;Encoding;Decoding;Costs;Computational complexity;Codes;Private computation;symmetric private polynomial computation;Lagrange encoding;computation complexity},
  doi = {10.1109/TIT.2022.3140890},
}

JSIT 2022

A Systematic Approach Towards Efficient Private Matrix Multiplication

Jinbao Zhu, and Songze Li

IEEE Journal on Selected Areas in Information Theory, 2022

Bib PDF

@article{9790818,
  author = {Zhu, Jinbao and Li, Songze},
  journal = {IEEE Journal on Selected Areas in Information Theory},
  title = {A Systematic Approach Towards Efficient Private Matrix Multiplication},
  year = {2022},
  volume = {3},
  number = {2},
  pages = {257-274},
  keywords = {Codes;Costs;Security;Indexes;Data privacy;Computational complexity;Task analysis;Coded distributed computing;fully private matrix multiplication;lagrange codes;polynomial codes;private and secure matrix multiplication;secure matrix multiplication},
  doi = {10.1109/JSAIT.2022.3181144},
}

ISIT 2022

Generalized Lagrange Coded Computing: A Flexible Computation-Communication Tradeoff

Jinbao Zhu, and Songze Li

In 2022 IEEE International Symposium on Information Theory (ISIT) , 2022

Bib PDF

@inproceedings{9834535,
  author = {Zhu, Jinbao and Li, Songze},
  booktitle = {2022 IEEE International Symposium on Information Theory (ISIT)},
  title = {Generalized Lagrange Coded Computing: A Flexible Computation-Communication Tradeoff},
  year = {2022},
  volume = {},
  number = {},
  pages = {832-837},
  keywords = {Privacy;Interpolation;Codes;Interference;Robustness;Encoding;Computational efficiency;coded distributed computing;Lagrange polynomial interpolation;interference cancellation;security and privacy},
  doi = {10.1109/ISIT50566.2022.9834535},
}

arXiv

Secure Federated Clustering

Songze Li, Sizai Hou, Baturalp Buyukates, and 1 more author

2022

Bib PDF

@misc{li2022securefederatedclustering,
  title = {Secure Federated Clustering},
  author = {Li, Songze and Hou, Sizai and Buyukates, Baturalp and Avestimehr, Salman},
  year = {2022},
  eprint = {2205.15564},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2205.15564},
}

arXiv

Fully Privacy-Preserving Federated Representation Learning via Secure Embedding Aggregation

Jiaxiang Tang, Jinbao Zhu, Songze Li, and 2 more authors

2022

Bib PDF

@misc{cryptoeprint:2022/784,
  author = {Tang, Jiaxiang and Zhu, Jinbao and Li, Songze and Zhang, Kai and Sun, Lichao},
  title = {Fully Privacy-Preserving Federated Representation Learning via Secure Embedding Aggregation},
  howpublished = {Cryptology ePrint Archive, Paper 2022/784},
  year = {2022},
  url = {https://eprint.iacr.org/2022/784},
}

2021

TIFS 2021

PolyShard: Coded Sharding Achieves Linearly Scaling Efficiency and Security Simultaneously

Songze Li, Mingchao Yu, Chien-Sheng Yang, and 3 more authors

IEEE Transactions on Information Forensics and Security, 2021

Bib PDF

@article{9141331,
  author = {Li, Songze and Yu, Mingchao and Yang, Chien-Sheng and Avestimehr, Amir Salman and Kannan, Sreeram and Viswanath, Pramod},
  journal = {IEEE Transactions on Information Forensics and Security},
  title = {PolyShard: Coded Sharding Achieves Linearly Scaling Efficiency and Security Simultaneously},
  year = {2021},
  volume = {16},
  number = {},
  pages = {249-261},
  keywords = {Throughput;Scalability;Encoding;Secure storage;Time measurement;Scalability;blockchain;security and trust;decentralized networks;coded sharding;information theory},
  doi = {10.1109/TIFS.2020.3009610},
}

Lightsecagg: Rethinking secure aggregation in federated learning

Chien-Sheng Yang, Jinhyun So, Chaoyang He, and 1 more author

2021

FL-ICML 2021

OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning

Jiacheng Liang, Wensi Jiang, and Songze Li

CoRR, 2021

Bib PDF

@article{DBLP:journals/corr/abs-2107-05252,
  author = {Liang, Jiacheng and Jiang, Wensi and Li, Songze},
  title = {OmniLytics: {A} Blockchain-based Secure Data Market for Decentralized
                    Machine Learning},
  journal = {CoRR},
  volume = {abs/2107.05252},
  year = {2021},
  url = {https://arxiv.org/abs/2107.05252},
  eprinttype = {arXiv},
  eprint = {2107.05252},
  timestamp = {Tue, 20 Jul 2021 15:08:33 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2107-05252.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

TCOM 2021

Compressed Coded Distributed Computing

Ahmed Roushdy Elkordy, Songze Li, Mohammad Ali Maddah-Ali, and 1 more author

IEEE Transactions on Communications, 2021

Bib PDF

@article{9336731,
  author = {Elkordy, Ahmed Roushdy and Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  journal = {IEEE Transactions on Communications},
  title = {Compressed Coded Distributed Computing},
  year = {2021},
  volume = {69},
  number = {5},
  pages = {2773-2783},
  keywords = {Task analysis;Training;Distributed computing;Encoding;Bandwidth;Multicast communication;Machine learning;MapReduce;distributed training;gradient aggregation;coded multicasting},
  doi = {10.1109/TCOMM.2021.3054906},
}

2020

NeurIPS SpicyFL workshop

FedML: A Research Library and Benchmark for Federated Machine Learning

Chaoyang He, Songze Li, Jinhyun So, and 17 more authors

2020

Bib PDF

@misc{he2020fedmlresearchlibrarybenchmark,
  title = {FedML: A Research Library and Benchmark for Federated Machine Learning},
  author = {He, Chaoyang and Li, Songze and So, Jinhyun and Zeng, Xiao and Zhang, Mi and Wang, Hongyi and Wang, Xiaoyang and Vepakomma, Praneeth and Singh, Abhishek and Qiu, Hang and Zhu, Xinghua and Wang, Jianzong and Shen, Li and Zhao, Peilin and Kang, Yan and Liu, Yang and Raskar, Ramesh and Yang, Qiang and Annavaram, Murali and Avestimehr, Salman},
  year = {2020},
  eprint = {2007.13518},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2007.13518},
}

FC 2020
Coded Merkle Tree: Solving Data Availability Attacks in Blockchains

Mingchao Yu, Saeid Sahraei, Songze Li, and 3 more authors

In Financial Cryptography and Data Security , 2020

Abs Bib PDF

In this paper, we propose coded Merkle tree (CMT), a novel hash accumulator that offers a constant-cost protection against data availability attacks in blockchains, even if the majority of the network nodes are malicious. A CMT is constructed using a family of sparse erasure codes on each layer, and is recovered by iteratively applying a peeling-decoding technique that enables a compact proof for data availability attack on any layer. Our algorithm enables any node to verify the full availability of any data block generated by the system by just downloading a }}\backslashvarTheta (1)}}byte block hash commitment and randomly sampling }}\backslashvarTheta (\backslashlog b)}}bytes, where b is the size of the data block. With the help of only one connected honest node in the system, our method also allows any node to verify any tampering of the coded Merkle tree by just downloading }}\backslashvarTheta (\backslashlog b)}}bytes. We provide a modular library for CMT in Rust and Python and demonstrate its efficacy inside the Parity Bitcoin client.
@inproceedings{10.1007/978-3-030-51280-4_8, author = {Yu, Mingchao and Sahraei, Saeid and Li, Songze and Avestimehr, Salman and Kannan, Sreeram and Viswanath, Pramod}, editor = {Bonneau, Joseph and Heninger, Nadia}, title = {Coded Merkle Tree: Solving Data Availability Attacks in Blockchains}, booktitle = {Financial Cryptography and Data Security}, year = {2020}, publisher = {Springer International Publishing}, address = {Cham}, pages = {114--134}, isbn = {978-3-030-51280-4}, }

arXiv

TaiJi: Longest Chain Availability with BFT Fast Confirmation

Songze Li, and David Tse

2020

Bib PDF

@misc{li2020taijilongestchainavailability,
  title = {TaiJi: Longest Chain Availability with BFT Fast Confirmation},
  author = {Li, Songze and Tse, David},
  year = {2020},
  eprint = {2011.11097},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2011.11097},
}

2019

AISTATS 2019
Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy

Qian Yu, Songze Li, Netanel Raviv, and 3 more authors

In Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics , 2019

Abs Bib PDF

We consider a scenario involving computations over a massive dataset stored distributedly across multiple workers, which is at the core of distributed learning algorithms. We propose Lagrange Coded Computing (LCC), a new framework to simultaneously provide (1) resiliency against stragglers that may prolong computations; (2) security against Byzantine (or malicious) workers that deliberately modify the computation for their benefit; and (3) (information-theoretic) privacy of the dataset amidst possible collusion of workers. LCC, which leverages the well-known Lagrange polynomial to create computation redundancy in a novel coded form across workers, can be applied to any computation scenario in which the function of interest is an arbitrary multivariate polynomial of the input dataset, hence covering many computations of interest in machine learning. LCC significantly generalizes prior works to go beyond linear computations. It also enables secure and private computing in distributed settings, improving the computation and communication efficiency of the state-of-the-art. Furthermore, we prove the optimality of LCC by showing that it achieves the optimal tradeoff between resiliency, security, and privacy, i.e., in terms of tolerating the maximum number of stragglers and adversaries, and providing data privacy against the maximum number of colluding workers. Finally, we show via experiments on Amazon EC2 that LCC speeds up the conventional uncoded implementation of distributed least-squares linear regression by up to 13.43\times, and also achieves a 2.36\times-12.65\times speedup over the state-of-the-art straggler mitigation strategies.
@inproceedings{pmlr-v89-yu19b, title = {Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy}, author = {Yu, Qian and Li, Songze and Raviv, Netanel and Kalan, Seyed Mohammadreza Mousavi and Soltanolkotabi, Mahdi and Avestimehr, Salman A.}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {1215--1225}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v89/yu19b.html}, }
PODC 2019
Coded State Machine – Scaling State Machine Execution under Byzantine Faults

Songze Li, Saeid Sahraei, Mingchao Yu, and 3 more authors

In Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing , Toronto ON, Canada, 2019

Abs Bib PDF

We introduce Coded State Machine (CSM), an information-theoretic framework to securely and efficiently execute multiple state machines on Byzantine nodes. The standard method of solving this problem is using State Machine Replication, which achieves high security at the cost of low efficiency. CSM simultaneously achieves the optimal linear scaling in storage, throughput, and security with increasing network size. The storage is scaled via the design of Lagrange coded states and coded input commands that require the same storage size as their origins. The computational efficiency is scaled using a novel delegation algorithm, called INTERMIX, which is an information-theoretically verifiable matrix-vector multiplication algorithm of independent interest.
@inproceedings{10.1145/3293611.3331573, author = {Li, Songze and Sahraei, Saeid and Yu, Mingchao and Avestimehr, Salman and Kannan, Sreeram and Viswanath, Pramod}, title = {Coded State Machine -- Scaling State Machine Execution under Byzantine Faults}, year = {2019}, isbn = {9781450362177}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3293611.3331573}, doi = {10.1145/3293611.3331573}, booktitle = {Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing}, pages = {150–152}, numpages = {3}, keywords = {verifiable computing, state machine execution, security, information theory, computational efficiency, byzantine faults}, location = {Toronto ON, Canada}, series = {PODC '19}, }

2018

TIT 2018

A Fundamental Tradeoff Between Computation and Communication in Distributed Computing

Songze Li, Mohammad Ali Maddah-Ali, Qian Yu, and 1 more author

IEEE Transactions on Information Theory, 2018

Bib PDF

@article{8051074,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Yu, Qian and Avestimehr, A. Salman},
  journal = {IEEE Transactions on Information Theory},
  title = {A Fundamental Tradeoff Between Computation and Communication in Distributed Computing},
  year = {2018},
  volume = {64},
  number = {1},
  pages = {109-128},
  keywords = {Encoding;Distributed databases;Benchmark testing;Electrical engineering;Electronic mail;Distributed computing;MapReduce;computation-communication tradeoff;coded multicasting;coded TeraSort},
  doi = {10.1109/TIT.2017.2756959},
}

NeurIPS 2018

Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training

Youjie Li, Mingchao Yu, Songze Li, and 3 more authors

In Advances in Neural Information Processing Systems , 2018

Bib PDF

@inproceedings{NEURIPS2018_2c6a0bae,
  author = {Li, Youjie and Yu, Mingchao and Li, Songze and Avestimehr, Salman and Kim, Nam Sung and Schwing, Alexander},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Bengio, S. and Wallach, H. and Larochelle, H. and Grauman, K. and Cesa-Bianchi, N. and Garnett, R.},
  pages = {},
  publisher = {Curran Associates, Inc.},
  title = {Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training},
  url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/2c6a0bae0f071cbbf0bb3d5b11d90a82-Paper.pdf},
  volume = {31},
  year = {2018},
}

IPDPSW 2018

Near-Optimal Straggler Mitigation for Distributed Gradient Methods

Songze Li, Seyed Mohammadreza Mousavi Kalan, A. Salman Avestimehr, and 1 more author

In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) , 2018

Bib PDF

@inproceedings{8425504,
  author = {Li, Songze and Mousavi Kalan, Seyed Mohammadreza and Avestimehr, A. Salman and Soltanolkotabi, Mahdi},
  booktitle = {2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
  title = {Near-Optimal Straggler Mitigation for Distributed Gradient Methods},
  year = {2018},
  volume = {},
  number = {},
  pages = {857-866},
  keywords = {Training;Computational modeling;Encoding;Task analysis;Distributed databases;Data models;Distributed gradient methods;Straggler mitigation;Near optimal recovery threshold;Near optimal communication load;Coupon's collector;Heterogeneous cluster},
  doi = {10.1109/IPDPSW.2018.00137},
}

NeurIPS 2018

GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

Mingchao Yu, Zhifeng Lin, Krishna Narra, and 6 more authors

In Advances in Neural Information Processing Systems , 2018

Bib PDF

@inproceedings{NEURIPS2018_cf059682,
  author = {Yu, Mingchao and Lin, Zhifeng and Narra, Krishna and Li, Songze and Li, Youjie and Kim, Nam Sung and Schwing, Alexander and Annavaram, Murali and Avestimehr, Salman},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Bengio, S. and Wallach, H. and Larochelle, H. and Grauman, K. and Cesa-Bianchi, N. and Garnett, R.},
  pages = {},
  publisher = {Curran Associates, Inc.},
  title = {GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training},
  url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/cf05968255451bdefe3c5bc64d550517-Paper.pdf},
  volume = {31},
  year = {2018},
}

arXiv

Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

Songze Li, Seyed Mohammadreza Mousavi Kalan, Qian Yu, and 2 more authors

CoRR, 2018

Bib PDF

@article{DBLP:journals/corr/abs-1805-09934,
  author = {Li, Songze and Kalan, Seyed Mohammadreza Mousavi and Yu, Qian and Soltanolkotabi, Mahdi and Avestimehr, Amir Salman},
  title = {Polynomially Coded Regression: Optimal Straggler Mitigation via Data
                    Encoding},
  journal = {CoRR},
  volume = {abs/1805.09934},
  year = {2018},
  url = {http://arxiv.org/abs/1805.09934},
  eprinttype = {arXiv},
  eprint = {1805.09934},
  timestamp = {Wed, 21 Oct 2020 19:29:39 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-1805-09934.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

ISIT 2018

Compressed Coded Distributed Computing

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2018 IEEE International Symposium on Information Theory (ISIT) , 2018

Bib PDF

@inproceedings{8437882,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2018 IEEE International Symposium on Information Theory (ISIT)},
  title = {Compressed Coded Distributed Computing},
  year = {2018},
  volume = {},
  number = {},
  pages = {2032-2036},
  keywords = {},
  doi = {10.1109/ISIT.2018.8437882},
}

2017

IEEE Commun Mag

Coding for Distributed Fog Computing

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

IEEE Communications Magazine, 2017

Bib PDF

@article{7901473,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  journal = {IEEE Communications Magazine},
  title = {Coding for Distributed Fog Computing},
  year = {2017},
  volume = {55},
  number = {4},
  pages = {34-40},
  keywords = {Bandwidth;Encoding;Edge computing;Redundancy;Time factors;Encoding;Computer architecture},
  doi = {10.1109/MCOM.2017.1600894},
}

TON 2017

A Scalable Framework for Wireless Distributed Computing

Songze Li, Qian Yu, Mohammad Ali Maddah-Ali, and 1 more author

IEEE/ACM Transactions on Networking, 2017

Bib PDF

@article{7935426,
  author = {Li, Songze and Yu, Qian and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  journal = {IEEE/ACM Transactions on Networking},
  title = {A Scalable Framework for Wireless Distributed Computing},
  year = {2017},
  volume = {25},
  number = {5},
  pages = {2643-2654},
  keywords = {Wireless communication;Distributed computing;Encoding;Mobile communication;Uplink;Downlink;Communication system security;Wireless distributed computing;edge computing;coding;information theory;scalability},
  doi = {10.1109/TNET.2017.2702605},
}

IPDPSW 2017

Coded TeraSort

Songze Li, Sucha Supittayapornpong, Mohammad Ali Maddah-Ali, and 1 more author

In 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) , 2017

Bib PDF

@inproceedings{7965073,
  author = {Li, Songze and Supittayapornpong, Sucha and Maddah-Ali, Mohammad Ali and Avestimehr, Salman},
  booktitle = {2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
  title = {Coded TeraSort},
  year = {2017},
  volume = {},
  number = {},
  pages = {389-398},
  keywords = {Encoding;Sorting;Machine learning algorithms;Distributed databases;Redundancy;Benchmark testing;Distributed Computing;Machine Learning;Sorting;MapReduce;Data Shuffling;Coding},
  doi = {10.1109/IPDPSW.2017.33},
}

ICC 2017

How to optimally allocate resources for coded distributed computing?

Qian Yu, Songze Li, Mohammad Ali Maddah-Ali, and 1 more author

In 2017 IEEE International Conference on Communications (ICC) , 2017

Bib PDF

@inproceedings{7996730,
  author = {Yu, Qian and Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2017 IEEE International Conference on Communications (ICC)},
  title = {How to optimally allocate resources for coded distributed computing?},
  year = {2017},
  volume = {},
  number = {},
  pages = {1-7},
  keywords = {Servers;Resource management;Distributed databases;Encoding;Cloud computing;Distributed processing},
  doi = {10.1109/ICC.2017.7996730},
}

ISIT 2017

Communication-aware computing for edge processing

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2017 IEEE International Symposium on Information Theory (ISIT) , 2017

Bib PDF

@inproceedings{8007057,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2017 IEEE International Symposium on Information Theory (ISIT)},
  title = {Communication-aware computing for edge processing},
  year = {2017},
  volume = {},
  number = {},
  pages = {2885-2889},
  keywords = {Mobile communication;Edge computing;Interference;Information theory;Mobile computing;Base stations;Smart phones},
  doi = {10.1109/ISIT.2017.8007057},
}

FWC 2017

Architectures for coded mobile edge computing

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2017 IEEE Fog World Congress (FWC) , 2017

Bib

@inproceedings{8368530,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2017 IEEE Fog World Congress (FWC)},
  title = {Architectures for coded mobile edge computing},
  year = {2017},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Computer architecture;Edge computing;Encoding;Computational modeling;Wireless communication;Load modeling;Automobiles},
  doi = {10.1109/FWC.2017.8368530},
}

2016

GC Wkshps2016

A Unified Coding Framework for Distributed Computing with Straggling Servers

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2016 IEEE Globecom Workshops (GC Wkshps) , 2016

Bib PDF

@inproceedings{7848828,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2016 IEEE Globecom Workshops (GC Wkshps)},
  title = {A Unified Coding Framework for Distributed Computing with Straggling Servers},
  year = {2016},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Servers;Encoding;Bandwidth;Multicast communication;Computational modeling;Electrical engineering},
  doi = {10.1109/GLOCOMW.2016.7848828},
}

54th Annual Allerton

Coded Distributed Computing: Straggling Servers and Multistage Dataflows

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton) , 2016

Bib

@inproceedings{7852225,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)},
  title = {Coded Distributed Computing: Straggling Servers and Multistage Dataflows},
  year = {2016},
  volume = {},
  number = {},
  pages = {164-171},
  keywords = {Servers;Encoding;Bandwidth;Computational modeling;Distributed databases;Electrical engineering},
  doi = {10.1109/ALLERTON.2016.7852225},
}

GLOBECOM 2016

Edge-Facilitated Wireless Distributed Computing

Songze Li, Qian Yu, Mohammad Ali Maddah-Ali, and 1 more author

In 2016 IEEE Global Communications Conference (GLOBECOM) , 2016

Bib

@inproceedings{7841765,
  author = {Li, Songze and Yu, Qian and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2016 IEEE Global Communications Conference (GLOBECOM)},
  title = {Edge-Facilitated Wireless Distributed Computing},
  year = {2016},
  volume = {},
  number = {},
  pages = {1-7},
  keywords = {Distributed computing;Wireless communication;Downlink;Uplink;Computational modeling;Mobile communication;Encoding},
  doi = {10.1109/GLOCOM.2016.7841765},
}

ACSSC 2016

Coded distributed computing: Fundamental limits and practical challenges

Songze Li, Qian Yu, Mohammad Ali Maddah-Ali, and 1 more author

In 2016 50th Asilomar Conference on Signals, Systems and Computers , 2016

Bib

@inproceedings{7869092,
  author = {Li, Songze and Yu, Qian and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2016 50th Asilomar Conference on Signals, Systems and Computers},
  title = {Coded distributed computing: Fundamental limits and practical challenges},
  year = {2016},
  volume = {},
  number = {},
  pages = {509-513},
  keywords = {Encoding;Sorting;Distributed databases;Bandwidth;Servers;Approximation algorithms},
  doi = {10.1109/ACSSC.2016.7869092},
}

SEC 2016

Poster Abstract: A Scalable Coded Computing Framework for Edge-Facilitated Wireless Distributed Computing

Songze Li, Qian Yu, Mohammad Ali Maddah-Ali, and 1 more author

In 2016 IEEE/ACM Symposium on Edge Computing (SEC) , 2016

Bib

@inproceedings{7774676,
  author = {Li, Songze and Yu, Qian and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2016 IEEE/ACM Symposium on Edge Computing (SEC)},
  title = {Poster Abstract: A Scalable Coded Computing Framework for Edge-Facilitated Wireless Distributed Computing},
  year = {2016},
  volume = {},
  number = {},
  pages = {79-80},
  keywords = {Wireless communication;Mobile communication;Encoding;Mobile computing;Uplink;Cloud computing;Wireless Distributed Computing;Scalable Distributed Computing;Edge-Facilitated Data Shuffling;MapReduce;Repetitive Computation Assignments;Coded Multicasting},
  doi = {10.1109/SEC.2016.11},
}

2015

53rd Annual Allerton

Coded MapReduce

Songze Li, Mohammad Ali Maddah-Ali, and A. Salman Avestimehr

In 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) , 2015

Bib PDF

@inproceedings{7447112,
  author = {Li, Songze and Maddah-Ali, Mohammad Ali and Avestimehr, A. Salman},
  booktitle = {2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)},
  title = {Coded MapReduce},
  year = {2015},
  volume = {},
  number = {},
  pages = {964-971},
  keywords = {Servers;Encoding;Electrical engineering;Cache memory;Local area networks;Multicast communication;Programming},
  doi = {10.1109/ALLERTON.2015.7447112},
}

ISIT 2016

Rover-to-orbiter communication in Mars: Taking advantage of the varying topology

Songze Li, David T.H. Kao, and A. Salman Avestimehr

In 2015 IEEE International Symposium on Information Theory (ISIT) , 2015

Bib PDF

@inproceedings{7282531,
  author = {Li, Songze and Kao, David T.H. and Avestimehr, A. Salman},
  booktitle = {2015 IEEE International Symposium on Information Theory (ISIT)},
  title = {Rover-to-orbiter communication in Mars: Taking advantage of the varying topology},
  year = {2015},
  volume = {},
  number = {},
  pages = {631-635},
  keywords = {Topology;Encoding;Receivers;Network topology;Mars;Transmitters;Upper bound;Mars;Rover-to-Orbiter Communication;Xchannel;Varying Topologies;Coding Across Topologies},
  doi = {10.1109/ISIT.2015.7282531},
}

2014

ICASSP 2014

Power allocation for Gaussian multiple access channel with noisy cooperative links

Songze Li, Emrah Akyol, and Urbashi Mitra

In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2014

Bib

@inproceedings{6853641,
  author = {Li, Songze and Akyol, Emrah and Mitra, Urbashi},
  booktitle = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Power allocation for Gaussian multiple access channel with noisy cooperative links},
  year = {2014},
  volume = {},
  number = {},
  pages = {474-478},
  keywords = {Transmitters;Resource management;Noise measurement;Wireless sensor networks;Convex functions;Wireless communication;Educational institutions;multiple access channel;cooperation cost;power allocation;convex optimization},
  doi = {10.1109/ICASSP.2014.6853641},
}

2013

ICASSP 2013

Cooperative spectrum sharing with joint receiver decoding

Songze Li, Urbashi Mitra, and Ashish Pandharipande

In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing , 2013

Bib

@inproceedings{6638674,
  author = {Li, Songze and Mitra, Urbashi and Pandharipande, Ashish},
  booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  title = {Cooperative spectrum sharing with joint receiver decoding},
  year = {2013},
  volume = {},
  number = {},
  pages = {5298-5302},
  keywords = {Decoding;Joints;Noise;Receivers;Protocols;Cognitive radio;Radio transmitters;spectrum sharing;cognitive radio;joint decoding;outage performance;virtual MIMO system},
  doi = {10.1109/ICASSP.2013.6638674},
}

2012

CISS 2012

Jointly cooperative decode-and-forward relaying for secondary spectrum access

Songze Li, Urbashi Mitra, Vishnu Ratnam, and 1 more author

In 2012 46th Annual Conference on Information Sciences and Systems (CISS) , 2012

Bib

@inproceedings{6310719,
  author = {Li, Songze and Mitra, Urbashi and Ratnam, Vishnu and Pandharipande, Ashish},
  booktitle = {2012 46th Annual Conference on Information Sciences and Systems (CISS)},
  title = {Jointly cooperative decode-and-forward relaying for secondary spectrum access},
  year = {2012},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Strontium;Decoding;Protocols;Transmitters;Markov processes;Receivers;Relays},
  doi = {10.1109/CISS.2012.6310719},
}