5 papers
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
Yueyang Quan, Anjun Gao, Yufei Xia +2
Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also exposes a critical security vulnerab…
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
Anjun Gao, Yueyang Quan, Yufei Xia +2
Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms through crafted prompts, while ne…
Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems
Yufei Xia, Anjun Gao, Yueyang Quan +2
Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new ch…
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Anjun Gao, Yueyang Quan, Yufei Xia +2
Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existi…
Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
Yu Xia, Zhouhang Xie, Xin Xu +4
Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Exist…