9 papers
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…
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…
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
Zesen Liu, Zihan Zhang, Dongdong She
Summarization-based prompt compression is increasingly used by LLM agents to shorten long, distributed contexts, but it shifts the security boundary: filters inspect the pre-compre…
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…
Machine learning inference of fission yields from gamma spectroscopy for very low-yield nuclear test verification
Julien de Troullioud de Lanversin, Jiehui Li, Christopher Fichtlscherer +2
Very low-yield nuclear tests pose a major verification challenge for the zero-yield standard of the Comprehensive Nuclear-Test-Ban Treaty (CTBT). The zero-yield standard prohibits…
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…