Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
This addresses the computational burden for researchers and practitioners needing to balance accuracy and robustness in adversarial defenses, though it is incremental as it builds on existing adversarial training methods.
The paper tackles the problem of efficiently exploring the trade-off between standard and robust accuracies in adversarial training without retraining, proposing Once-for-All Adversarial Training (OAT) that allows adjusting this trade-off at testing time, achieving similar or superior performance to dedicatedly trained models.
Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. Moreover, the training process is heavy and hence it becomes impractical to thoroughly explore the trade-off between accuracy and robustness. This paper asks this new question: how to quickly calibrate a trained model in-situ, to examine the achievable trade-offs between its standard and robust accuracies, without (re-)training it many times? Our proposed framework, Once-for-all Adversarial Training (OAT), is built on an innovative model-conditional training framework, with a controlling hyper-parameter as the input. The trained model could be adjusted among different standard and robust accuracies "for free" at testing time. As an important knob, we exploit dual batch normalization to separate standard and adversarial feature statistics, so that they can be learned in one model without degrading performance. We further extend OAT to a Once-for-all Adversarial Training and Slimming (OATS) framework, that allows for the joint trade-off among accuracy, robustness and runtime efficiency. Experiments show that, without any re-training nor ensembling, OAT/OATS achieve similar or even superior performance compared to dedicatedly trained models at various configurations. Our codes and pretrained models are available at: https://github.com/VITA-Group/Once-for-All-Adversarial-Training.