6 papers
MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
Tailun Chen, Yu He, Yan Wang +9
Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated…
AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
Yan Wang, Xuguang Ai, Jaisal Patel +7
Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone. A model must link reported…
WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
Jinnan Yang, Yan Wang, Zhen Bi +5
Diffusion Large Language Models (DLMs) have demonstrated significant advantages across various tasks. However, constrained by their multi-step iterative inference mechanism, their…
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Yan Wang, Zhixuan Chu, Zihao Xue +9
Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…
Thought Purity: A Defense Framework For Chain-of-Thought Attack
Zihao Xue, Zhen Bi, Long Ma +7
Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial…
Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
Weijie Wang, Peizhuo Lv, Yan Wang +7
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a key technique for enhancing Large Language Models (LLMs) with proprietary Knowledge Graphs (KGs) in knowledge-inten…