通过监督对比学习增强深度神经网络的对抗鲁棒性
Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
AI总结：
本文提出结合监督对比学习与基于间隔的对比损失的新框架，通过优化特征空间结构和决策边界间隔，在CIFAR-100和ResNet-18上提升了对抗鲁棒性。
摘要：
对抗攻击通过引入难以察觉的扰动导致卷积神经网络误分类，从而利用其特征表示和决策边界的弱点。本文提出了一种结合监督对比学习和基于间隔的对比损失的新框架，以增强对抗鲁棒性。监督对比学习通过聚类同类样本的嵌入并分离不同类样本的嵌入来改善特征空间的结构。基于间隔的对比损失受支持向量机启发，施加显式约束以创建具有明确间隔的鲁棒决策边界。在CIFAR-100数据集上使用ResNet-18骨干网络进行的实验表明，在快速梯度符号法攻击下，对抗准确率方面的鲁棒性性能有所提升。
英文摘要：
Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper presents a novel framework combining supervised contrastive learning and margin-based contrastive loss to enhance adversarial robustness. Supervised contrastive learning improves the structure of the feature space by clustering embeddings of samples within the same class and separating those from different classes. Margin-based contrastive loss, inspired by support vector machines, enforces explicit constraints to create robust decision boundaries with well-defined margins. Experiments on the CIFAR-100 dataset with a ResNet-18 backbone demonstrate robustness performance improvements in adversarial accuracy under Fast Gradient Sign Method attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
