作者位次 #4/9ACL 2026Poster· Natural Language Processing
MM - P oison RAG : Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
Hyeonjeong Ha · Qiusi Zhan · Jeonghwan Kim · Dimitrios Bralios · Saikrishna Sanniboina · Nanyun Peng · Kai-Wei Chang · Daniel Kang · Heng Ji
摘要
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 multi...