4 papers
MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
YuFei Luo, Xiucheng Xu, Zhen Yang
Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory systems can be traced to two recurr…
Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
Junke Zhang, Jianwei Wang, Sishuo Chen +3
Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is important for…
EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
Tianyun Zhang, Zhen Yang, Haozhao Wang +2
Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed threshold…
Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
Tong Zhang, Ru Zhang, Jianyi Liu +2
Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and e…