English(EN) SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning

新的SEBA框架实现了对视觉强化学习的样本高效黑盒攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了SEBA，一个旨在高效发起针对视觉强化学习智能体的黑盒对抗性攻击的新框架。该方法整合了一个影子Q模型来估计对抗条件下的奖励，一个生成对抗网络来创建不易察觉的扰动，以及一个世界模型来最小化真实世界查询。SEBA在MuJoCo和Atari等基准测试中，通过减少累积奖励和保持视觉保真度方面取得了显著成功，同时比以前的方法需要更少的环境交互。 AI

影响这项研究通过突出对对抗性攻击的脆弱性，可能导致更强大的视觉强化学习智能体。

排序理由该集群包含一篇学术论文，详细介绍了视觉强化学习对抗性攻击的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 31 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了视觉强化学习对抗性攻击的新方法。[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: paper, safety; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Tairan Huang, Yulin Jin, Junxu Liu, Qingqing Ye, Haibo Hu · 2026-09-02 04:00

SEBA：视觉强化学习的样本高效黑盒攻击

arXiv:2511.09681v2 Announce Type: replace-cross Abstract: Visual reinforcement learning has achieved remarkable progress in visual control and robotics, but its vulnerability to adversarial perturbations remains underexplored. Most existing black-box attacks focus on vector-based…

本文如何被排名

报道来源 [1]

SEBA：视觉强化学习的样本高效黑盒攻击

相关实体

相关话题