Improved robustness to adversarial examples using Lipschitz regularization of the loss
This addresses the problem of adversarial vulnerability in machine learning models, offering incremental improvements with verifiable guarantees.
The paper tackles improving adversarial robustness by augmenting adversarial training with worst-case adversarial training, resulting in an 11% increase in robustness over state-of-the-art on CIFAR-10 under the ℓ₂ norm.
We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the norm of the gradient of the loss. We interpret adversarial training as Total Variation Regularization, which is a fundamental tool in mathematical image processing, and WCAT as Lipschitz regularization.