MrM is a black-box membership inference attack on multimodal RAG systems that masks key objects in a target image and uses the system's ability to reconstruct them as a membership signal.
Rule: Reliable multimodal rag for factuality in medical vision language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems
MrM is a black-box membership inference attack on multimodal RAG systems that masks key objects in a target image and uses the system's ability to reconstruct them as a membership signal.