17 papers
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
Pengfei He, Lesly Miculicich, Vishesh Sharma +5
Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt in…
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
Yuping Lin, Jiayuan Ding, Yue Xing +3
KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation,…
Retrieval Heads are Dynamic
Yuping Lin, Zitao Li, Yue Xing +6
Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on st…
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Pengfei He, Zhenwei Dai, Xianfeng Tang +9
Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable message…
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Shen Dong, Shaochen Xu, Pengfei He +5
Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised mem…
Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
Pengfei He, Ash Fox, Lesly Miculicich +7
Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to li…