MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks 事件

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks arXiv:2502.17832v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has become a common practice in multimodal large language models (MLLM) to enhance factual grounding and reduce hallucination. Yet, its reliance on retrieval exposes MLLMs to knowledge poisoning attacks, in which adversaries deliberately inject malicious multimodal content into external knowledge bases to steer models towa