Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
This provides a more efficient alternative to adversarial training for improving classifier robustness against adversarial attacks, potentially enabling use on complex datasets.
The paper tackles the high computational cost of adversarial training by showing that simple regularization methods like label smoothing and logit squeezing, combined with Gaussian noise injection, can achieve strong adversarial robustness without generating adversarial examples, often exceeding adversarial training performance.
Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often precludes adversarial training from use on complex image datasets. In this study, we explore the mechanisms by which adversarial training improves classifier robustness, and show that these mechanisms can be effectively mimicked using simple regularization methods, including label smoothing and logit squeezing. Remarkably, using these simple regularization methods in combination with Gaussian noise injection, we are able to achieve strong adversarial robustness -- often exceeding that of adversarial training -- using no adversarial examples.