When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines
Researchers have developed a new framework called CRCP to address corpus poisoning attacks in Retrieval-Augmented Generation (RAG) systems. Existing attacks often fail when faced with realistic RAG pipelines that include chunking and reranking stages. CRCP aims to overcome this by optimizing for retrieval relevance, reranker consistency, and robustness across chunk boundaries, demonstrating significantly higher attack success rates in experiments. AI
IMPACT Highlights a realism gap in RAG security evaluations, suggesting new methods are needed to defend against sophisticated poisoning attacks.