#artificial intelligence
Jun 2024
BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
A novel threat is unveiled in which attackers steer the RAG system's response by injecting malicious passages into its knowledge base, enabling the attacker to steer the response without altering the user input or modifying the RAG weights.
Jiaqi Xue, Meng Zheng, Yebowen Hu et al.
· arXiv.org · 109 citations
· ⚡8