CiteShade: טיהור ציטציות בהפצת תשובות עם קישורים למקורות

תקציר מקורי באנגליתarXiv:2609.15660v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model's answers on retrieved external knowledge and returns each answer with citations that identify its sources. Those citations are the user's audit trail: they let a reader verify a claim without trusting the model. Prior security work on RAG asks whether an attacker can corrupt the answer, leaving the citation channel unexplored. We show that this channel is a new and practical attack surface. We propose CiteShade, the first citation laundering attack to RAG, in which an attacker controlling a single source induces a model to produce an attacker-chosen wrong answer and to attribute it to a trusted source that does not support it, while the evidence for the correct answer remains in