Welcome to S3IC Lab!
The research lab for Secure, Scalable, and ReSponsible Intelligent Computation (S3IC), led by Prof. Songze Li, works on a wide range of research topics to improve security, scalability, and trustworthiness of distributed computing frameworks, focusing on the applications of machine learning, artificial intelligence, and blockchain.
Our current research areas include:
1) Safety, privacy, and security of large language models;
2) Secure multi-party computation for AI;
3) Blockchain scalability and privacy.
We are always looking for strongly motivated PhD and Master students, Undergraduate students, Post-docs, Research assistants, and Visitors/interns to join our lab. Interested applicants please email your CV, transcript, and any related publications to songzeli [at] seu [dot] edu [dot] cn, or songzeli8824 [at] outlook [dot] com.
News
| Jun 09, 2025 | Our paper “Secure Embedding Aggregation for Cross-Silo Federated Representation Learning” is accepted to IEEE Transactions on Information Forensics & Security. |
|---|---|
| May 27, 2025 | Our paper “PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning” is accepted to IEEE Transactions on Information Forensics & Security. Congratulations to Sizai! |
| May 04, 2025 | Our paper “Resolving the Efficiency-Utility Dilemma of Threshold Linearly Homomorphic Encryption via Message-Space Adapter” is accepted to Crypto 2025. Congratulations to Yijia! |
| Apr 30, 2025 | Our paper “SecurePay: Enabling Secure and Fast Payment Processing for Platform Economy” is accepted to IWQoS 2025. |
| Mar 11, 2025 | Our paper “TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models” is accepted to NAACL 2025 Workshop on Privacy in NLP (Oral). |
| Feb 27, 2025 | Our paper “DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders” is accepted to CVPR 2025. Congratulations to Sizai! |
| Jan 23, 2025 | Our paper “Agent-Oriented Planning in Multi-Agent Systems” is accepted to ICLR 2025. |
| Jan 20, 2025 | Our paper “Arbitrary-Threshold Fully Homomorphic Encryption with Lower Complexity” is accepted to USENIX Security 2025. Congratulations to Yijia! |