MIRAGE: manipulation-immune RAG with adaptive guard against textual evidence attacks
Abstract Retrieval-augmented generation (RAG) substantially improves large language models (LLMs) on knowledge-intensive tasks by incorporating external knowledge, yet open knowledge sources introduce prominent security risks. The SafeRAG benchmark identifies four novel textual evidence manipulation attacks, namely sil...
Qiao Yuan, Feiyang Li, Yi Jiang et al.
· Cybersecurity · 0 citations