7 papers
Twin Agent: Context Residual Compression for Privilege Separated Agents
Zhanhao Hu, Dennis Jacob, Xiao Huang +3
Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Exist…
RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery
Muxi Lyu, Karen Shieh, Yiwei Hou +3
Cross-Site Scripting (XSS) remains one of the most prevalent and damaging classes of web vulnerabilities. LLM-based coding agents offer a promising approach to XSS discovery by com…
Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases
Yiwei Hou, Hao Wang, Muxi Lyu +6
Memory safety vulnerabilities remain a significant threat even for projects with extensive fuzzing and manual auditing. Recent results suggest that large language models hold great…
GradShield: Alignment Preserving Finetuning
Zhanhao Hu, Xiao Huang, Patrick Mendoza +4
Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some…
JULI: Jailbreak Large Language Models by Self-Introspection
Jesson Wang, Zhanhao Hu, David Wagner
Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-align…
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob +7
Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulne…