English(EN) Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

新的证据对抗训练提高了人工智能的鲁棒性和不确定性

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

研究人员推出了一种名为证据对抗训练（EV-AT）的新方法，旨在提高神经网络预测不确定性的鲁棒性和可靠性，特别适用于安全关键型应用。该方法解决了对抗训练提高准确性但损害不确定性估计的常见问题。EV-AT 利用狄利克雷分布来模拟不确定性，并结合了用于干净准确性和可靠不确定性的基于证据的损失，以及匹配干净和对抗性预测的鲁棒证据对齐损失。实验表明，EV-AT 在平衡鲁棒性和不确定性方面优于现有的对抗训练方法。 AI

影响通过同时提高鲁棒性和不确定性估计，增强了安全关键型人工智能应用的可靠性。

排序理由该集群包含一篇研究论文，详细介绍了一种提高人工智能模型鲁棒性和不确定性的新方法。[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: 0 / 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，详细介绍了一种提高人工智能模型鲁棒性和不确定性的新方法。[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, safety, model release; 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: 93 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.LG TIER_1 English(EN) · Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt · 2026-07-07 04:00

鲁棒性与不确定性并存：用于鲁棒选择性分类的证据对抗训练

arXiv:2607.03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable. Adversarial training is a widely adopted defense for improving robustness in deep neural networks; however, its effect on the reliability of predict…

本文如何被排名

报道来源 [1]

鲁棒性与不确定性并存：用于鲁棒选择性分类的证据对抗训练

相关实体

相关话题