Vision-language-action models are highly vulnerable to membership inference attacks, including practical black-box versions that exploit generated actions and motion trajectories.
CoRRabs/2510.10932(2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
VLA-Hijack is a new adversarial patch attack on Vision-Language-Action models that suppresses real arm features and injects the patch as surrogate embodiment to achieve high cross-architecture transferability.
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.
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.
-
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
VLA-Hijack is a new adversarial patch attack on Vision-Language-Action models that suppresses real arm features and injects the patch as surrogate embodiment to achieve high cross-architecture transferability.
-
TRAP: Tail-aware Ranking Attack for World-Model Planning
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses