English(EN) A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection

新型对抗性示例欺骗AI模型，但人类仍能识别

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-28 04:00

研究人员引入了一种新型对抗性示例，与典型的攻击不同，它使用大而可见的扰动来欺骗AI模型，同时人类仍能识别。这种新方法在MNIST、CIFAR-10和ImageNet等数据集上进行了测试，揭示了一个显著的差距：模型保持高准确率，而人类识别率却显著下降。标准的分布外（OOD）检测方法未能识别出这些示例，尽管一个特征空间马氏距离检测器有效，但容易受到自适应攻击。现有的防御措施，包括对抗性训练，并未有效缓解该攻击的成功。 AI

影响突显了AI模型的新漏洞，表明当前的防御和OOD检测方法不足以应对人类可识别的扰动。

排序理由关于AI模型新型对抗性示例的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于AI模型新型对抗性示例的学术论文。[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: 44 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。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ali Borji · 2026-07-28 04:00

一种新型对抗性示例：衡量人机模型差距及其与OOD检测的关系

arXiv:2607.22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep its original, correct prediction, even though a h…

本文如何被排名

报道来源 [1]

一种新型对抗性示例：衡量人机模型差距及其与OOD检测的关系

相关实体

相关话题