MA‐CAT: Misclassification‐Aware Contrastive Adversarial Training
Authors:
Open Access
- 5 February 2024
- journal article
- research article
- Published by Wiley in Advanced Intelligent Systems
- Vol. 6 (5)
Abstract
Vulnerability to adversarial examples poses a significant challenge to the secure application of deep neural networks. Adversarial training and its variants have shown great potential in addressing this problem. However, such approaches, which directly optimize the decision boundary, often result in overly complex adversarial decision boundaries that are detrimental to generalization. To deal with this issue, a novel plug‐and‐play method known as Misclassification‐Aware Contrastive Adversarial Training (MA‐CAT) from the perspective of data distribution optimization is proposed. MA‐CAT leverages supervised decoupled contrastive learning to cluster nature examples within the same class in the logit space, indirectly increasing the margins of examples. Moreover, by taking into account the varying difficulty levels of adversarial training for different examples, MA‐CAT adaptively customizes the strength of adversarial training for each example using an instance‐wise misclassification‐aware adaptive temperature coefficient. Extensive experiments on the CIFAR‐10, CIFAR‐100, and SVHN datasets demonstrate that MA‐CAT can be easily integrated into existing models and significantly improves robustness with minimal computational cost.Keywords
This publication has 15 references indexed in Scilit:
- Randomized Adversarial Training via Taylor Expansion2023
- The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training2023
- Decoupled Contrastive Learning2022
- Understanding the Behaviour of Contrastive Loss2021
- Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search2020
- The security of machine learning in an adversarial setting: A surveyJournal of Parallel and Distributed Computing, 2019
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Identity Mappings in Deep Residual Networks2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- Evasion Attacks against Machine Learning at Test Time2013