C-LEAD: Contrastive Learning for Enhanced Adversarial Defense 文章

ArXiv CS.CV2026-06-02NEWSen作者: Suklav Ghosh, Sonal Kumar, Arijit Sur

摘要

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 incorrect predictions with small perturbations in input images. Addressing this issue is crucial for deploying robust deep-learning systems. This paper presents a novel approach that utilizes contrastive learning for adversarial defense, a previously unexplored area. Our method leverages the contrastive loss function to enhance the robustness of classification models by training them with both clean and adversarially perturbed images. By optimizing the model's parameters alongside the perturbations, our approach enables the network to learn robust representations that are less susceptible to adversarial attacks.

相关事件查看全部 (1)

arXiv:2510.27249v2 论文发布
BREAKTHROUGH影响: medium

相关公司

暂无数据

相关人物

暂无数据

相关产品

暂无数据