Bag of Tricks for Adversarial Training
share
Adversarial training (AT) is one of the most effective strategies for promoting model robustness. However, recent benchmarks show that most of the proposed improvements on AT are less effective than simply early stopping the training procedure. This counter-intuitive fact motivates us to investigate the implementation details of tens of AT methods. Surprisingly, we find that the basic training settings (e.g., weight decay, learning rate schedule, etc.) used in these methods are highly inconsistent, which could largely affect the model performance as shown in our experiments. For example, a slightly different value of weight decay can reduce the model robust accuracy by more than 7 which is probable to override the potential promotion induced by the proposed methods. In this work, we provide comprehensive evaluations on the effects of basic training tricks and hyperparameter settings for adversarially trained models. We provide a reasonable baseline setting and re-implement previous defenses to achieve new state-of-the-art results.
READ FULL TEXT