4 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…
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…
MiniScope: Authorizing Agents with Least-Privilege Permissions
Jinhao Zhu, Kevin Tseng, Gil Vernik +4
AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security challenge. Existing…
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…