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.
CoRR abs/2510.09269(2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
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.
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses