3 papers
cs.CV2026
CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
Hui Lu, Zhijie Peng, Yuqi Lin +8
Vision-Language-Action (VLA) policies are vulnerable to localized physical perturbations, yet existing certified patch defenses target discrete labels and cannot directly certify c…
cs.AI2026
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
Hui Lu, Yi Yu, Yiming Yang +6
Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly…
cs.CV2026
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
Hui Lu, Yi Yu, Yiming Yang +5
Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single…