4 papers
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Zhaoqi Wang, Daqing He, Zijian Zhang +13
While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption att…
StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering
Yuelyu Ji, Zhuochun Li, Hui Ji +1
We present \textbf{StepGap}, a hybrid NLI-LLM decision tree that detects step-level evidence gaps in multi-hop QA and emits one of three typed labels: \textsc{Contradicted Claim} (…
Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
Zhaoqi Wang, Zijian Zhang, Daqing He +5
Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harm…
Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
Zhaoqi Wang, Daqing He, Zijian Zhang +4
Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversa…