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 machine learning models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
ReMIA offers a practical privacy metric for synthetic data by training two generators and using a classifier to detect source dataset membership, achieving sensitivity comparable to standard MIAs with far less computation.
DistractMIA performs output-only black-box membership inference on vision-language models by inserting semantic distractors and measuring shifts in generated text responses.
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.
AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
SIGIL introduces five canary strategies and a Neyman-Pearson-based Membership Inference Score that achieves AUC 0.831-0.947 in 36,000 simulations, remaining above 0.86 even after full paraphrasing.
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.
-
ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators
ReMIA offers a practical privacy metric for synthetic data by training two generators and using a classifier to detect source dataset membership, achieving sensitivity comparable to standard MIAs with far less computation.
-
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.
-
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.
-
Amplifying Membership Signal Through Chained Regeneration
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
-
Subtle Injection for Ground-truth Inference of LLM Training Data
SIGIL introduces five canary strategies and a Neyman-Pearson-based Membership Inference Score that achieves AUC 0.831-0.947 in 36,000 simulations, remaining above 0.86 even after full paraphrasing.