arXiv Computation and Language By Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu, Ying-Dar Lin, Yu-Sung Wu, Wei-Bin Lee

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

Read the original on arXiv Computation and Language →

The paper introduces TRACE, a lightweight framework for detecting corpus poisoning in Retrieval-Augmented Generation systems. TRACE works by tracing answer-related tokens through token influence attribution, first identifying recurrent high-influence keywords across retrieved documents and then verifying their impact on model predictions. Experiments on three QA benchmarks and six large language models show that TRACE achieves strong detection performance while also revealing attacker-specified target answers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning
Jul 30

RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning

arXiv:2607. 26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously injected passages that manipulate retrieved evidence.

By Pushkal Kumar, Tucker Nielson, Tanish Kolhe, Shubham Zala, Vincent Li
arXiv AI
Aug 26

RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation

RAGSentinel is a training‑free, label‑free defense designed for black‑box retrieval‑augmented generation systems. It employs a surrogate encoder to detect hidden‑state shifts caused by retrieved documents, removes shared topic directions, and filters poisoned documents as geometric outliers from a robust majority consensus. The method is proven to recover a poison‑free majority context under honest‑majority and representation‑separation assumptions, and experiments show it keeps attack success rates low while maintaining accuracy across multiple datasets, LLM families, and adaptive attacks.

By Yueyang Quan, Anjun Gao, Yufei Xia, Minghong Fang, Zhuqing Liu