English(EN) C-LEAD: Contrastive Learning for Enhanced Adversarial Defense

对比学习提升AI对抗攻击的防御能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-02 04:00

研究人员推出了一种新方法C-LEAD，该方法利用对比学习来提高深度神经网络对抗对抗性攻击的防御能力。该方法在训练模型时同时使用干净和扰动图像，并与扰动一起优化参数，以学习更具弹性的特征。实验表明，模型在抵抗各种对抗性扰动方面的鲁棒性得到了显著增强，这表明对比损失在深度学习中提取鲁棒特征方面是有效的。 AI

影响增强AI模型抵御恶意输入的能力，对安全部署至关重要。

排序理由这是一篇详细介绍改进AI模型鲁棒性新方法的学术论文。 [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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; 这是一篇详细介绍改进AI模型鲁棒性新方法的学术论文。 [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: 137 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.CV TIER_1 English(EN) · Suklav Ghosh, Sonal Kumar, Arijit Sur · 2026-06-02 04:00

C-LEAD：对比学习增强对抗性防御

arXiv:2510.27249v2 Announce Type: replace Abstract: Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorre…

本文如何被排名

报道来源 [1]

C-LEAD：对比学习增强对抗性防御

相关实体

相关话题