English(EN) ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning

新的ATLAS框架可高效发现AI模型的对抗性输入集

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员开发了ATLAS（自适应信任区域用于潜在对抗性搜索），一个新颖的基于查询的框架，旨在高效地发现可能导致黑盒学习系统失败的对抗性输入集。ATLAS将攻击生成构建为主动学习的水平集估计问题，结合了校准近似和局部-全局采样架构，以识别包含对抗性示例的输入空间区域。该方法旨在构建代表性的对抗性集合，准确反映目标模型的鲁棒性，在MNIST、CIFAR和ImageNet等标准和对抗性训练模型上优于现有的基于查询的黑盒攻击。 AI

影响这项研究通过能够更好地识别漏洞，可能带来更鲁棒的AI系统。

排序理由该集群包含一篇详细介绍机器学习模型对抗性攻击新框架的研究论文。[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: 19 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍机器学习模型对抗性攻击新框架的研究论文。[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) · Marsalis Gibson, Claire Tomlin, Shankar Sastry · 2026-10-07 04:00

ATLAS-AL: 基于主动学习的自适应信任区域用于潜在对抗搜索

arXiv:2610.07323v1 Announce Type: new Abstract: Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover \textit{sets} of inputs that induce model …

本文如何被排名

报道来源 [1]

ATLAS-AL: 基于主动学习的自适应信任区域用于潜在对抗搜索

相关实体

相关话题