Research · curated 21 Jul 2026
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
First reported aclanthology.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
MM-PoisonRAG demonstrates that multimodal RAG pipelines can be reliably subverted through knowledge-base poisoning, a growing attack surface as defenders deploy retrieval-grounded MLLMs in production.
MM-PoisonRAG is a research paper presenting local and global knowledge poisoning attacks against multimodal retrieval-augmented generation (RAG) systems used by multimodal large language models (MLLMs). The work shows how injecting poisoned entries into the retrieval knowledge base can manipulate MLLM outputs, exploiting RAG's reliance on retrieved external content.