Research · curated 21 Jul 2026
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
First reported · updated · 2 reports aclanthology.org
Coverage timeline
Why it matters
MM-PoisonRAG shows that multimodal RAG systems widely used to reduce hallucination can be subverted through knowledge poisoning, a concern for defenders deploying retrieval-grounded MLLMs.
MM-PoisonRAG is a research paper presenting local and global knowledge poisoning attacks that disrupt multimodal retrieval-augmented generation (RAG) in multimodal large language models (MLLMs). The work demonstrates how MLLMs' reliance on retrieval exposes them to poisoned knowledge injected into the retrieval corpus, manipulating generated outputs.