English(EN) Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity

Robust CurveMoE 增强神经网络的对抗性防御能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 04:00

研究人员开发了 Robust CurveMoE，一个新颖的混合专家框架，旨在增强神经网络的对抗性防御能力。该方法通过低损耗路径连接针对不同扰动范数进行专门化的模型，使它们能够利用互补的鲁棒性特征。该框架有效地从特定的曲线位置导出专家模型，并选择性地将其应用于有影响力的层，同时在路由路径之间共享参数。在 CIFAR-100 和 ImageNet-100 数据集上的实验表明，与现有方法相比，Robust CurveMoE 在干净精度、范数特定精度和联合精度方面都有显著提高。 AI

影响引入了一种更有效的神经网络对抗性防御方法，有望提高模型在各种扰动下的安全性。

排序理由该集群包含一篇详细介绍新模型架构及其在基准测试中性能的研究论文。[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: 28 / 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新模型架构及其在基准测试中性能的研究论文。[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, 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: 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) · Xu Zhang, Ren Wang · 2026-08-27 04:00

Robust CurveMoE：面向混合专家模型的模态连通性多范数对抗性防御

arXiv:2608.26043v1 Announce Type: new Abstract: Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter configurat…

本文如何被排名

报道来源 [1]

Robust CurveMoE：面向混合专家模型的模态连通性多范数对抗性防御

相关实体

相关话题