12 citations · 17 across the 9 of their papers we have counts for
4 papers · 1 filter
Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
Chenlong Yin, Xiaolong Jin, Wei Zou +2
Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement lea…
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
Weifei Jin, Xilong Wang, Wei Zou +2
Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into…
Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Wei Zou, Mingwen Dong, Miguel Romero Calvo +7
Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack…
AgentWatcher: A Rule-based Prompt Injection Monitor
Yanting Wang, Wei Zou, Runpeng Geng +1
Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the…