具身开发者社区

外观

论文arXiv 2610.2356612 天前

通过闭环优化增强针对 VLA 模型的视觉任务重定向攻击 ​

提出 TRACO 以闭环优化增强定向视觉攻击，并在多个 VLA 模型和仿真环境中提升任务重定向成功率。

AI 整理
  • 本体 SDK 与控制
  • 仿真与训练
  • 具身模型

原文链接：Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization（arXiv 2610.23566 · 发布日期：2026-10-16）

Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization

提出 TRACO 以闭环优化增强定向视觉攻击，并在多个 VLA 模型和仿真环境中提升任务重定向成功率。

核心要点 ​

  • 既有攻击用固定目标监督，扰动会改变早期动作与后续物理状态。
  • TRACO 通过执行驱动监督，为攻击下到达的状态重建监督信号。
  • 进度引导选择在进展停滞处聚焦更新，并保持早期行为监督。
  • 实验显示 TRACO 在多个 VLA 模型和仿真环境中提高任务重定向成功率。

验证范围与局限：验证范围为多个 VLA 模型和仿真环境中的实验。

英文摘要 (Abstract) ​

Vision-language-action (VLA) models enable language-guided robot manipulation, but remain vulnerable to visual attacks that undermine user control over robot behavior. Prior studies optimize visual perturbations using fixed target supervision. However, the perturbation can change earlier actions and, in turn, the physical states reached later. As the attacked trajectory evolves, this supervision may no longer match the behavior needed at the states actually reached. Accurately matching these targets can therefore fail to advance the attacker-specified task. Even with suitable supervision, reducing average matching error does not ensure sustained task progress. The robot may still fail at a critical stage, and further updates can disrupt previously successful behavior. To address these limitations, we propose TRACO, a framework that enhances existing targeted visual attacks through closed-loop optimization. Its Execution-Driven Supervision rebuilds supervision for the states reached under attack to guide subsequent updates. Within this framework, Progress-Guided Selection focuses updates where progress stalls while maintaining supervision on the earlier behavior needed to reach that point. Experiments across VLA models and simulation environments show improved task-redirection success with TRACO, highlighting the security implications of closed-loop attack optimization.

作者：Chunjin Ye, Guanying Chen, Jianjie Huang, Jianhao Chen, Quanlin Chen, Hanjie Zhao, Haozhe Liang, Tieyun Qian, Xiaochun Cao

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.23566：Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization访问 2026-10-21