新的“状态后门”攻击针对具身AI模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-09 04:00

研究人员开发了一种针对视觉-语言-动作（VLA）模型的新型后门攻击，VLA模型对于机器人等具身AI应用至关重要。与依赖可见视觉触发器的先前方法不同，这种新颖的“状态后门”利用机器人手臂的初始状态作为触发器。研究人员采用了一种偏好引导的遗传算法来寻找最小但有效的基于状态的触发器，在不影响正常任务性能的情况下实现了超过90%的攻击成功率。 AI

影响揭示了具身AI的一个新漏洞，可能需要为机器人系统采取新的安全措施。

排序理由该集群包含一篇详细介绍AI模型新型攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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AI模型新型攻击方法的学术论文。[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; 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: 120 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。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Ji Guo, Wenbo Jiang, Yansong Lin, Yijing Liu, Ruichen Zhang, Guomin Lu, Aiguo Chen, Xinshuo Han, Hongwei Li · 2026-06-09 04:00

状态后门：面向状态空间中视觉-语言-动作模型的隐蔽现实世界投毒攻击

arXiv:2601.04266v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, …

本文如何被排名

报道来源 [1]

状态后门：面向状态空间中视觉-语言-动作模型的隐蔽现实世界投毒攻击

相关实体

相关话题