Vision-language-action models are highly vulnerable to membership inference attacks, including practical black-box versions that exploit generated actions and motion trajectories.
Membership inference attacks against large vision-language models.Advances in Neural Information Processing Systems, 37:98645–98674, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DistractMIA performs output-only black-box membership inference on vision-language models by inserting semantic distractors and measuring shifts in generated text responses.
citing papers explorer
-
Membership Inference Attacks on Vision-Language-Action Models
Vision-language-action models are highly vulnerable to membership inference attacks, including practical black-box versions that exploit generated actions and motion trajectories.
-
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.