ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks
ToxicRAG shows a single narrative-form poisoned document can steer RAG answers, achieving 0.61-0.91 attack success rates across four LLMs.
1 stories, newest first · one card per story
ToxicRAG shows a single narrative-form poisoned document can steer RAG answers, achieving 0.61-0.91 attack success rates across four LLMs.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views