English(EN) Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

新方法提高了黑盒对抗性攻击的效率

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-25 10:14

研究人员开发了一种名为机会主义目标选择（OTS）的新方法，以提高黑盒对抗性攻击的效率。OTS充当一个包装器，允许攻击在早期阶段从无目标目标切换到有目标目标，从而减少查询浪费。该技术无需修改底层攻击模型或访问梯度，并在ImageNet分类器上进行了验证，显示出成功率和查询效率的显著提高。 AI

影响提高了对抗性攻击的效率，可能影响AI模型鲁棒性测试和安全性。

排序理由该集群包含一篇详细介绍对抗性攻击新研究方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含一篇详细介绍对抗性攻击新研究方法的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 127 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Florent Tariolle, Florian Yger · 2026-05-26 04:00

机会性目标选择：查询高效黑盒对抗性攻击的早期定向承诺

arXiv:2605.25663v1 Announce Type: new Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, und…
arXiv cs.LG TIER_1 English(EN) · Florian Yger · 2026-05-25 10:14

机会性目标选择：查询高效黑盒对抗性攻击的早期定向承诺

Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected progress. We introduce Opportunistic Tar…