English(EN) BadWorld: Adversarial Attacks on World Models

新的BadWorld框架揭示了视觉世界模型的关键漏洞

作者 PulseAugur 编辑部 · [3 个来源] · 2026-06-15 00:00

研究人员开发了BadWorld，一个新颖的对抗性框架，旨在暴露视觉世界模型（VWMs）中的漏洞。该无标签系统会在图像中生成细微的扰动，导致模型在面对未见过的用户控件时，其未来预测也会出现灾难性故障。研究结果突显了在安全关键型应用中部署VWMs的重大风险，并提出了潜在的隐私保护机制。 AI

影响突显了在安全关键型系统中部署视觉世界模型的关键风险。

排序理由该集群包含一篇研究论文，详细介绍了用于视觉世界模型的新型对抗攻击框架。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-06-15 00:00

BadWorld: Adversarial Attacks on World Models

BadWorld is a label-free adversarial framework that reveals structural vulnerabilities in visual world models by generating imperceptible perturbations that cause catastrophic failures in future rollouts.
arXiv cs.CV TIER_1 English(EN) · Linghui Shen, Mingyue Cui, Xingyi Yang · 2026-06-16 04:00

BadWorld: Adversarial Attacks on World Models

arXiv:2606.16519v1 Announce Type: new Abstract: Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks …
arXiv cs.CV TIER_1 English(EN) · Xingyi Yang · 2026-06-15 10:21

BadWorld: Adversarial Attacks on World Models

Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attack…