Post #2238
137
Forwarded from AISec [x\x feed]🍓🍌🍆 (Artyom Semenov)
arXiv.org CleanBase: Detecting Malicious Documents in RAG Knowledge Databases Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge...- 👍 1