SyncAI.news, a Varaisys broadcasting
DMT-Attack: Diffusion-Prior Texture Search for Closed-Loop Vision-Language-Action Policies
JX

Jun Xia, Shangwen Wang, Jun Ma, Ruichao Ren, Zhouyang Jia, Xin Zhao, Huijun Liu, Jie Yu

· 1 min read

ResearcharXiv cs.AI

DMT-Attack: Diffusion-Prior Texture Search for Closed-Loop Vision-Language-Action Policies

arXiv:2611.25695v1 Announce Type: new Abstract: Vision-language-action (VLA) policies rely on visual feedback throughout manipulation, making them vulnerable to persistent texture attacks. However, optimized patterns can stand out from their surroundings, making an attack easier to notice and its carrier more likely to be inspected or removed. To address this limitation, our key insight is to search the structured image distribution of a diffusion model for natural-looking textures while using closed-loop feedback to identify task-disruptive candidates. Based on this idea, we propose DMT-Attack, a gradient-free gray-box attack that generates textures for ordinary scene objects such as tablecloths. A frozen text-conditioned diffusion model defines the search space, and an eight-expert latent proposal network is initialized from evaluated teacher latents and refined using rollout feedback. We evaluate DMT-Attack against pi_0.5 and OpenVLA-OFT across four LIBERO suites. DMT-Attack achieves a macro clean-conditioned attack success rate (cASR) of 57.9%, compared with 44.7% for UPA-RFAS and 19.7% for random natural textures. It also attains higher scene similarity and a lower clean-calibrated detector flag rate (45% versus 97.5-100% for optimized patch baselines). These results demonstrate that natural-looking textures can disrupt VLA visual feedback and closed-loop decision-making, motivating defenses that jointly assess visual appearance and task behavior.

Original source

This story was published by arXiv cs.AI and written by Jun Xia, Shangwen Wang, Jun Ma, Ruichao Ren, Zhouyang Jia, Xin Zhao, Huijun Liu, Jie Yu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News