English(EN) GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness

新的GRAPE框架提升神经网络的对抗鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员推出了一种新颖的训练框架GRAPE，旨在增强神经网络的对抗鲁棒性，同时保持模型尺寸紧凑。GRAPE的独特之处在于将鲁棒模型学习视为一个演化过程，逐步暴露和优化参数，而不是从一开始就依赖固定结构。这种引导式参数空间演化方法，包括渐进式隐藏扩展和对抗性谱利用分数，在CIFAR-10上与传统的对抗训练方法相比，在鲁棒准确性方面取得了显著的改进，即使在计算预算相当且参数数量减少的情况下也是如此。 AI

影响这项研究通过提高AI模型对对抗性攻击的抵御能力并降低计算开销，可能带来更安全、更高效的AI模型。

排序理由该集群包含一篇学术论文，详细介绍了一种提高AI模型鲁棒性的新方法。[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; 该集群包含一篇学术论文，详细介绍了一种提高AI模型鲁棒性的新方法。[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; 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: 114 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) · Zhiyuan Ye (University of Science and Technology of China), Xiangyu Zhou (China Mobile), Ji Qi (China Mobile), Hao Zhang (University of Science and Technology of China), Yi Zhou (China Mobile) · 2026-06-16 04:00

GRAPE：面向紧凑型对抗鲁棒性的引导式参数空间演化

arXiv:2606.14865v1 Announce Type: cross Abstract: Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start. This paper asks whether the order in which parameters become optimizable can affect the final robust solu…

本文如何被排名

报道来源 [1]

GRAPE：面向紧凑型对抗鲁棒性的引导式参数空间演化

相关实体

相关话题