CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense
CiteShade attack makes RAG models cite trusted sources for attacker-chosen wrong answers, raising wrong-answer rate from 0.01 to 0.68.
1 stories, newest first · one card per story
CiteShade attack makes RAG models cite trusted sources for attacker-chosen wrong answers, raising wrong-answer rate from 0.01 to 0.68.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views