paper-with-me

Papers

Secure Retrieval-Augmented Generation against Poisoning Attacks

2025-10-28 · Zirui Cheng, Jikai Sun, Anjun Gao, Yueyang Quan, Zhuqing Liu, Xiaohua Hu, Minghong Fang arxiv

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but also introduces security risks, particularly from data poisoning, where the attacker injects poisoned texts into the knowledge database to manipulate system outputs. While various defenses have been proposed, they often struggle against advanced attacks. To address this, we introduce RAGuard, a detection framework designed to identify poisoned texts. RAGuard first expands the retrieval scope to increase the proportion of clean texts, reducing the likelihood of retrieving poisoned content. It then applies chunk-wise perplexity filtering to detect abnormal variations and text similarity filtering to flag highly similar texts. This non-parametric approach enhances RAG security, and experiments on large-scale datasets demonstrate its effectiveness in detecting and mitigating poisoning attacks, including strong adaptive attacks.

📄 PDF Abstract BibTeX arXiv:2510.25025

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Practical Poisoning Attacks against Retrieval-Augmented Generation

2025-04-04 · Baolei Zhang, Yuxi Chen, Minghong Fang, Zhuqing Liu 외

Large language models (LLMs) have demonstrated impressive natural language processing abilities but face challenges such as hallucination and outdated knowledge. Retrieval-Augmented Generation (RAG) has emerged as a stat…

HallucinationRAGRetrievalRetrieval-augmented Generation

Traceback of Poisoning Attacks to Retrieval-Augmented Generation

2025-04-30 · Baolei Zhang, Haoran Xin, Minghong Fang, Zhuqing Liu 외

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) systems improve accuracy by leveraging external knowledge sources. However, recent research has revealed RAG's susceptibility to poisoning…

RAGRetrievalRetrieval-augmented Generation

Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems

2025-05-22 · Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo 외

Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the larg…

Adversarial AttackHallucinationPassage RankingRAG+2

Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks

2024-12-21 · Jinyan Su, Jin Peng Zhou, Zhengxin Zhang, Preslav Nakov 외

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adve…

RAGRetrievalRetrieval-augmented Generation

Provably Secure Retrieval-Augmented Generation

2025-08-01 · Pengcheng Zhou, Yinglun Feng, Zhongliang Yang arxiv

Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been systematically addressed yet. Existing defe…