7 papers · 1 filter
Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
Kaikai Zhang, Zihan Zhang, Yuchong Xie +4
Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under a finite budget. W…
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu +8
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity betwee…
Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents
Mingyu Luo, Zihan Zhang, Zesen Liu +7
LLM agents convert model outputs into consequential actions, including communications, code changes, and financial transactions. Developers often trust evidence such as test result…
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Zhixiang Zhang, Zesen Liu, Yuchong Xie +2
Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vec…
QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
Yuchong Xie, Zesen Liu, Mingyu Luo +7
Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injectio…
When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
Zesen Liu, Zhixiang Zhang, Yuchong Xie +1
Prompt compression is increasingly deployed in LLM agents to reduce latency and cost, but it also determines what the backend LLM ultimately sees. We show that, when trusted and un…
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Yuchong Xie, Mingyu Luo, Zesen Liu +7
Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation o…