AI agents powered by large language models (LLMs) can perform complex tasks but may harm the systems they operate in, either intentionally or unintentionally. Existing agent monitoring approaches rely on rule-based guardrails or LLM-based trace auditing. However, rule-based guardrails can be bypassed through obfuscatio...
E. Zhang, Cheng-Yun-King Yang, Dong-Yan Xu· 0 citations
The security of industrial control systems (ICS) is important. Yet most ICS security efforts focus on the detection of ICS attacks, with much less attention to the recovery after detection. In this paper, we address this underexplored area by jointly auditing the detection and recovery of ICS. Specifically, we define t...
Syed Ghazanfar Abbas, Gang Wang, Dong-Yan Xu· 0 citations
Self-issued authentication as a conversational security failure is identified: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state.
XSec is introduced, a self-explainable deep architecture developed for security applications that produces deterministic explanations for a fixed trained model and input and substantially reduces explanation latency compared with approximation-based and perturbation-based post-hoc methods.
Ananth Shreekumar, Jyun-Jhu Syu, Muslum Ozgur Ozmen et al.· Lecture notes in computer sc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.