An automated, feedback-guided attack generation pipeline is built and applied to Claude Code and Codex in their native runtimes, showing that production agents are vulnerable to context-aware, multi-step injection over long horizons.
Jing-Kai Liu, Yu-Fei Han, Xiaoting Lyu et al.· 0 citations
Large language models (LLMs) have shown strong potential for assisting software and security analysis tasks, yet their effectiveness in cryptographic symbolic protocol verification remains insufficiently understood. In this paper, we conduct the first systematic evaluation of the capability of state-of-the-art LLMs in...
It is shown that current scientific agents remain insufficiently robust to scientifically plausible perturbations, with failures often remaining undetected, propagating, and resisting recovery.
Xiaoting Lyu, Xin-Bo Ma, Yu-Fei Han et al.· arXiv.org· 0 citations
The findings reveal a confidentiality risk in LLM agents: protecting explicit artifacts alone is insufficient, as observable execution behavior can leak the procedural knowledge required to reconstruct proprietary task-solving capabilities in low-capability and attacker-controlled agents.
Xiaoting Lyu, Yu-Hong Wu, Yu-Fei Han et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.