Saved in:
Bibliographic Details
Main Authors: Wang, Longwei, Nayyem, Navid, Rakin, Abdullah
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.19747
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915081504161792
author Wang, Longwei
Nayyem, Navid
Rakin, Abdullah
author_facet Wang, Longwei
Nayyem, Navid
Rakin, Abdullah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19747
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
Wang, Longwei
Nayyem, Navid
Rakin, Abdullah
Machine Learning
Artificial Intelligence
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.
title Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.19747