CAT:Collaborative Adversarial Training

03/27/2023
by   Xingbin Liu, et al.
0

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods, we find different adversarial training methods have distinct robustness for sample instances. For example, a sample 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 observation, we propose a collaborative adversarial training framework to improve the robustness of neural networks. Specifically, we use different adversarial training methods to train robust models and let models interact with their knowledge during the training process. Collaborative Adversarial Training (CAT) can improve both robustness and accuracy. Extensive experiments on various networks and datasets validate the effectiveness of our method. CAT achieves state-of-the-art adversarial robustness without using any additional data on CIFAR-10 under the Auto-Attack benchmark. Code is available at https://github.com/liuxingbin/CAT.

READ FULL TEXT
research
09/01/2021

Towards Improving Adversarial Training of NLP Models

Adversarial training, a method for learning robust deep neural networks,...
research
03/13/2022

LAS-AT: Adversarial Training with Learnable Attack Strategy

Adversarial training (AT) is always formulated as a minimax problem, of ...
research
03/02/2021

Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Training

In this technical report, we evaluate the adversarial robustness of a ve...
research
10/22/2020

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

Adversarial training and its many variants substantially improve deep ne...
research
08/29/2021

DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks

Adversarial training has been proven to be a powerful regularization met...
research
09/27/2022

Inducing Data Amplification Using Auxiliary Datasets in Adversarial Training

Several recent studies have shown that the use of extra in-distribution ...
research
10/13/2022

Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors

Deep models often fail to generalize well in test domains when the data ...

Please sign up or login with your details

Forgot password? Click here to reset