DistractMIA performs output-only black-box membership inference on vision-language models by inserting semantic distractors and measuring shifts in generated text responses.
Membership inference attacks from first principles
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
FERMI improves membership inference on tabular diffusion models by mapping relational auxiliary information into attack features, raising TPR at 0.1 FPR by up to 53% white-box and 22% black-box over single-table baselines.
Logit-based MIAs perform comparably on MLLMs with or without visual inputs in-distribution but visual inputs mask membership signals in out-of-distribution settings.
citing papers explorer
-
DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
DistractMIA performs output-only black-box membership inference on vision-language models by inserting semantic distractors and measuring shifts in generated text responses.
-
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
FERMI improves membership inference on tabular diffusion models by mapping relational auxiliary information into attack features, raising TPR at 0.1 FPR by up to 53% white-box and 22% black-box over single-table baselines.
-
Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
Logit-based MIAs perform comparably on MLLMs with or without visual inputs in-distribution but visual inputs mask membership signals in out-of-distribution settings.