English(EN) Convex training of Lipschitz-regularized shallow neural networks

新的凸训练方法增强了神经网络对对抗性攻击的鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-19 04:00

研究人员开发了一种新颖的浅层神经网络训练方法，以增强其对对抗性攻击的抵抗能力。该技术通过首先引入一个可以有效优化以达到全局最优的凸约束，来解决一个非凸Lipschitz正则化训练问题。所提出的方法可以作为后处理步骤应用于现有的预训练网络，确保最终网络的性能不劣于初始网络。在真实数据集上的实验表明，与现有方法相比，这种凸训练程序产生的网络在目标值、准确性和对抗性扰动鲁棒性方面均有所提高。 AI

影响这项研究提供了一种提高神经网络安全性以及对抗恶意输入可靠性的方法。

排序理由该集群包含一篇学术论文，详细介绍了一种新的神经网络训练方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

Lipschitz-regularized shallow neural networks

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; 该集群包含一篇学术论文，详细介绍了一种新的神经网络训练方法。[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; 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: 111 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) · Chao Yin, Antoine Lesage-Landry · 2026-06-19 04:00

Lipschitz正则化浅层神经网络的凸训练

arXiv:2606.19652v1 Announce Type: new Abstract: In this work, we introduce a training procedure for shallow neural networks that promotes robustness against adversarial attacks. We solve a non-convex Lipschitz-regularized training program by introducing a convex restriction that …

本文如何被排名

报道来源 [1]

Lipschitz正则化浅层神经网络的凸训练

相关实体

相关话题