English(EN) STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks

新的STROKE攻击方法使用稀疏遮挡实现高效的黑盒对抗性示例

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-26 04:00

研究人员开发了STROKE，一种新颖的用于图像分类器的黑盒对抗性攻击方法。该技术利用简单的、稀疏的结构遮挡，特别是定向矩形，来创建扰动。与现有的基于补丁的攻击相比，STROKE在查询次数显著减少和计算时间缩短的情况下，展现了很高的攻击成功率，使其成为生成对抗性示例的一种高效且有效的方法。 AI

影响引入了一种更有效的生成对抗性攻击的方法，可能影响模型鲁棒性测试和安全性。

排序理由该集群包含一篇研究论文，详细介绍了一种用于计算机视觉模型对抗性攻击的新方法。 [lever_c_demoted from research: ic=1 ai=1.0]

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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了一种用于计算机视觉模型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, other; 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。

arXiv cs.CV TIER_1 English(EN) · Ankit Gupta, Akshat Pandya, Paul Lin, Christoph Adami, Emily Dolson · 2026-10-26 04:00

STROKE：简单稀疏结构遮挡用于黑盒对抗性攻击

arXiv:2610.32932v1 Announce Type: new Abstract: We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these perturbations through a lightweight greedy add-and-ref…