English(EN) RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples

新的RLGPA方法使用强化学习进行定向对抗攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了RLGPA，一种新颖的方法，它使用强化学习来指导为AI模型创建稀疏对抗样本的过程。该方法动态调度和调整扰动减少步骤的粒度，以优化有限的查询预算。RLGPA在图像分类任务的定向对抗成功率方面表现出显著的改进，尤其是在非常低的扰动水平下，其性能优于SparseEvo和Pointwise等现有方法。 AI

影响这项研究通过理解和改进攻击方法，可能有助于提高对抗攻击的鲁棒性防御。

排序理由详细介绍一种新的对抗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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新的对抗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: 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.LG TIER_1 English(EN) · Chao Zhou, Shenghua He, Jiaxin Mo, Qiangguo Yu, Fengchuang Xing · 2026-11-06 05:00

RLGPA：一种基于强化学习引导的粒度规划攻击，用于基于决策的稀疏对抗样本

arXiv:2611.07512v1 Announce Type: new Abstract: Decision-based sparse attacks must reduce perturbation support using only the victim's predicted label. The best restoration strategy varies as support contracts: coarse removal works early, while tail states need finer, history-awa…

本文如何被排名

报道来源 [1]

RLGPA：一种基于强化学习引导的粒度规划攻击，用于基于决策的稀疏对抗样本

相关实体

相关话题