Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention

Abstract:Retrieval Augmented Generation (RAG) is a highly effective paradigm for keeping LLM-based responses up-to-date and reducing the likelihood of hallucinations. Yet, RAG was recently shown to be quite vulnerable to corpus knowledge poisoning: an attacker injects misleading documents to the corpus to steer an LLM's output to an undesired response. We argue that the standard causal attention mechanism in LLMs enables harmful cross-document interactions, specifically in cases of attacks. Accordingly, we introduce a novel defense approach for RAG: Sparse Document Attention RAG (SDAG). This is a block-sparse attention mechanism that disallows cross-attention between retrieved documents. SDAG requires a minimal inference-time change to the attention mask. We present an empirical evaluation of LLM-based question answering (QA) with a variety of attack strategies on RAG. We show that our SDAG method substantially outperforms the standard causal attention mechanism. We further demonstrate the clear merits of integrating SDAG with state-of-the-art RAG defense methods. Specifically, the integration results in performance that is statistically significantly better than the state-of-the-art.

Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)

arXiv:2602.04711 [cs.IR]

(or arXiv:2602.04711v3 [cs.IR] for this version)

https://doi.org/10.48550/arXiv.2602.04711 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.