Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses
- 19 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-14
Abstract
Adversarial training (AT) is considered to be one of the most reliable defenses against adversarial attacks. However, models trained with AT sacrifice standard accuracy and do not generalize well to unseen attacks. Some examples of recent works show generalization improvement with adversarial samples under unseen threat models are, on-manifold threat model or neural perceptual threat model. However, the former requires exact manifold information while the latter requires algorithm relaxation. Motivated by these considerations, we propose a novel threat model called Joint Space Threat Model (JSTM), which exploits the underlying manifold information with Normalizing Flow, ensuring that the exact manifold assumption holds. Under JSTM, we develop novel adversarial attacks and defenses. Specifically, we propose the Robust Mixup strategy in which we maximize the adversity of the interpolated images and gain robustness and prevent overfitting. Our experiments show that Interpolated Joint Space Adversarial Training (IJSAT) achieves good performance in standard accuracy, robustness, and generalization. IJSAT is also flexible and can be used as a data augmentation method to improve standard accuracy and combined with many existing AT approaches can improve robustness. We demonstrate the effectiveness of our approach on three benchmark datasets, CIFAR-10/100, OM-ImageNet and CIFAR-10-C.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Interpolated Adversarial Training2019
- Resisting Adversarial Attacks Using Gaussian Mixture Variational AutoencodersProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Boosting Adversarial Attacks with Momentum2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Towards Evaluating the Robustness of Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Fast R-CNN2015
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012