Generalizing Adversarial Robustness with Confidence-Calibrated Adversarial Training in PyTorch

Taking adversarial training from this previous article as baseline, this article introduces a new, confidence-calibrated variant of adversarial training that addresses two significant flaws: First, trained with L_∞ adversarial examples, adversarial training is not robust against L₂ ones. Second, it incurs a significant increase in (clean) test error. Confidence-calibrated adversarial training addresses these problems by encouraging lower confidence on adversarial examples and subsequently rejecting them.

The post Generalizing Adversarial Robustness with Confidence-Calibrated Adversarial Training in PyTorch appeared first …

adversarial machine learning article blog computer vision confidence deep learning error examples flaws machine learning python pytorch robustness test training