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

May 15, 2026	Our paper “When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems” is accepted to USENIX Security 2026. Congratulations to Chenqing!
May 01, 2026	Two papers are accepted to ICML 2026: Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective. Congratulations to Puwei! Budget-Efficient Attacks and Robustness Training for Cooperative MARL.
Apr 07, 2026	Our paper “MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization” is accepted to ACL 2026. Congratulations to Yongtong!
Jan 17, 2026	Our paper “Sleight: Hidden Data Privacy Breaches in Federated Learning” is accepted to IEEE Transactions on Dependable and Secure Computing.
Dec 04, 2025	Our paper “Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography” is accepted to NDSS 2026. Congratulations to Jiameng!
Sep 21, 2025	Prof. Songze Li is awarded 2025 ACM SIGSAC China Rising Star Award!
Jul 08, 2025	Our paper “How does Watermarking Affect Visual Language Models in Document Understanding?” is accepted to Conference on Language Modeling (COLM) 2025. Congratulations to Chunxue!
Jun 09, 2025	Our paper “Secure Embedding Aggregation for Cross-Silo Federated Representation Learning” is accepted to IEEE Transactions on Information Forensics & Security.