SOURCE-LINKED INTELLIGENCE

CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global