News

• Oct 2026Check out LLM & Agent Security and Privacy, a searchable index of LLM and agent security and privacy papers from the top four security conferences.
• Sep 2026A preprint on “Activation-Conditioned Self-Distillation” is now available on arXiv. PDF
• Sep 2026A preprint on membership inference against on-policy distillation, “Leaky Students: Membership Inference against On-Policy Distillation”, is now available on arXiv. PDF
• Jan 2026Our paper “SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA” has been accepted to ICLR 2026. PDF
• Dec 2025Our paper “In-Context Probing for Membership Inference in Fine-Tuned Language Models” has been accepted to NDSS 2026. Congratulations to Zhexi! PDF Code
• Aug 2025A preprint on selective homomorphic encryption for joint federated learning in cross-device scenarios is now available on arXiv. PDF
• Aug 2025A preprint on the dynamics of membership privacy in deep learning is now available on arXiv. PDF
• Jun 2025Our paper “On the Adversarial Robustness of Graph Neural Networks with Graph Reduction” has been accepted to ESORICS 2025. Congratulations to our undergraduate researcher Kerui Wu! PDF Code
• Apr 2025Our paper “Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble” has been accepted to CCS 2025. Congratulations to our undergraduate researchers Zhiqi Wang (first author), Chengyu Zhang, and Yuetian Chen! PDF Code
• Jan 2025Our paper “Privacy and Accuracy-Aware AI/ML Model Deduplication” has been accepted to SIGMOD 2025. PDF
• Dec 2024A preprint on the adversarial robustness of graph neural networks is now available on arXiv. PDF
• Sep 2024Our paper “CMASan: Custom Memory Allocator-aware Address Sanitizer” has been accepted to the IEEE Symposium on Security and Privacy (S&P) 2025. PDF Code
• Aug 2024Served on the TPC for AsiaCCS 2025.
• Aug 2024Our paper “On the Robustness of Graph Reduction Against GNN Backdoor” has been accepted to the 17th ACM Workshop on Artificial Intelligence and Security (AISec 2024). PDF
• Apr 2024Our paper “Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control” has been accepted to IJCAI 2024. PDF Code
• Feb 2024Our survey on privacy in vertical federated learning is now available on arXiv. If you’re interested in VFL privacy research, please check it out! PDF
• Jan 2024A preprint on LLM-guided backdoor attacks is now available on arXiv. PDF Code
• Dec 2023Invited to serve as a PC member for IEEE ICDCS 2024 (Track of Security, Privacy, and Trust in Distributed Systems).
• Nov 2023We have been awarded an AIRC RPI-IBM research grant.
• Sep 2023Our paper “A Comparison of End-to-End Decision Forest Inference Pipelines” has been accepted to ACM SoCC 2023. Thanks to all the co-authors!
• Jun 2023Our paper “Privacy-Preserving Redaction of Diagnosis Data through Source Code Analysis” has been accepted to SSDBM 2023. Many thanks to Lixi, Prof. Jia Zou, and Hong Min!