English(EN) Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

新的攻击方法针对深度强化学习代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-08 04:00

研究人员开发了一种新的轨迹级对抗攻击方法，旨在针对深度强化学习（DRL）代理。该方法利用环境的可微分模型和温度平滑的代理策略，在递缩视界上优化扰动序列。在各种深度Q网络（DQN）和双重DQN（DDQN）代理的CartPole-v1环境上的实验表明，这种轨迹级攻击在白盒、跨模型和跨算法场景中显著优于标准的每步攻击和随机噪声。 AI

影响这项研究突显了深度强化学习代理的潜在漏洞，表明需要更强大的安全措施。

排序理由该集群是发表在arXiv上的研究论文，详细介绍了一种新的攻击方法。[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: 7 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群是发表在arXiv上的研究论文，详细介绍了一种新的攻击方法。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Zexin Li, Ruili Yao, Yiming Zeng, Xiaoxue Gao · 2026-10-08 04:00

增强深度强化学习的可迁移对抗性攻击

arXiv:2610.06083v2 Announce Type: replace Abstract: Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based black-box attacks on DRL: the attacker crafts observat…

本文如何被排名

报道来源 [1]

增强深度强化学习的可迁移对抗性攻击

相关实体

相关话题