CAT: Collaborative Adversarial Training

xingbin liu, Huafeng Kuang, Xianming Lin, GUANNAN JIANG, YONGJIAN WU, Xi Wang, Rongrong Ji

Abstract:

Adversarial training can improve the robustness of neural networks. Previous adversarial training methods focus on a single training strategy and do not consider the collaboration between different training strategies. In this paper, we find different adversarial training methods have distinct robustness for sample instances. For example, an instance can be correctly classified by a model trained using standard adversarial training (AT) but not by a model trained using TRADES, and vice versa. Based on this phenomenon, we propose a collaborative adversarial training framework to improve the robustness of neural networks. Specifically, we simultaneously use different adversarial training methods to train two robust models from scratch. We input the adversarial examples generated by each network to the peer network and use the logit of the peer network to guide the training of its network. Collaborative Adversarial Training (CAT) can improve both robustness and accuracy. Finally, Extensive experiments on CIFAR-10 and CIFAR-100 validated the effectiveness of our method.
CAT achieved new state-of-the-art robustness without using any additional data on CIFAR-10 under the Auto-Attack benchmark.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)