C-LEAD: Contrastive Learning for Enhanced Adversarial Defense
This addresses the problem of adversarial robustness for deploying reliable deep-learning systems in computer vision, representing a novel application in an unexplored area.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing a novel approach using contrastive learning for adversarial defense, resulting in significant improvements in model robustness against various adversarial perturbations.
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. Experimental results show significant improvements in the model's robustness against various types of adversarial perturbations. This suggests that contrastive loss helps extract more informative and resilient features, contributing to the field of adversarial robustness in deep learning.