13 papers
: An End-to-End Agent Auditing Engine
Haoning Wang, Mingxun Zhang, Chenyue Yu +4
With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving ha…
Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
Jianing Geng, Ruiqi He, Zekun Fei +6
Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and private deployment behind cloud-…
Do LLMs Know Their Vulnerable Scenarios?
Ziheng Peng, Huiqi Deng, Haoran Jing +5
Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teami…
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Xuan Liu, Hefeng Zhou, Sicheng Chen +6
When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as fo…
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
Mingxuan Zhang, Jiahui Han, Dadi Guo +5
LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than t…
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Tianyi Zhou, Dongrui Liu, Leitao Yuan +2
LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building su…