English(EN) Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

新的DURA攻击使用扩散模型操纵机器人

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-12 04:00

研究人员开发了一种名为DURA的新方法，该方法使用扩散模型为视觉-语言-动作（VLA）模型创建视觉上自然的对抗性补丁。这些补丁可以操纵机器人执行非预期操作，对实际应用构成重大安全风险。DURA在白盒和黑盒场景中都有效，在模拟和物理测试中均优于现有攻击方法，凸显了VLA系统改进防御的必要性。 AI

影响突出了机器人控制系统中关键的安全漏洞，有必要开发更强大的防御措施来抵御对抗性攻击。

排序理由该集群包含一篇详细介绍针对AI模型的新攻击方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍针对AI模型的新攻击方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 57 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Jiahui Han, Yuhui Yao, Xin Wang, Jiafei Cao, Mingxuan Zhang, Danfeng Shan, Huiqi Deng, Guanchu Wang, Xia Hu · 2026-08-12 04:00

隐藏在眼皮底下：基于扩散的无限制机器人对视觉-语言-动作模型的攻击

arXiv:2608.10393v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial robustness remains largely underexplored, and exploiting this weakness can lead t…