AI RESEARCH
Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks
arXiv CS.AI
•
ArXi:2601.17644v3 Announce Type: replace-cross The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA)