AIBearisharXiv – CS AI · 7h ago7/10
🧠
DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
Researchers introduce DiscourseFlip, a novel attack method against Retrieval-Augmented Generation (RAG) systems that manipulates opinions across multiple related queries by poisoning retrieval content at the discourse level. Unlike previous attacks targeting individual queries, this coordinated approach induces broader opinion shifts while evading detection, and existing defenses prove ineffective against it.