Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks

arXiv:2601.17644v3 Announce Type: replace-cross Abstract: The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces important privacy challenges. In particular, while mRAG provides a practical capability to connect...