4 papers
What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
Yuanbo Xie, Wenlei Zhu, Tianyun Liu +5
Modern agentic systems fundamentally reshape the security boundary of LLMs by introducing persistent system state including memories, filesystems, tools, and other long-lived conte…
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
Yuanbo Xie, Yingjie Zhang, Tianyun Liu +2
Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two signific…
SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents
Wenyuan Zhang, Tianyun Liu, Mengxiao Song +2
Despite the abundance of prior social strategies possessed by humans, there remains a paucity of research dedicated to their transfer and integration into social agents. Our propos…
FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
Shiyao Cui, Zhenyu Zhang, Yilong Chen +4
The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and tox…