Improved robustness to adversarial examples using Lipschitz regularization of the loss
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.
Code (1)
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Lipschitz regularized Deep Neural Networks generalize and are adversarially robust
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does n…
Adversarial RobustnessLightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples
How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\epsilon$-robust, consume huge resources, they can only achieve small degree…
Achieving robustness in classification using optimal transport with hinge regularization
Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with cl…
Adversarial RobustnessBinary ClassificationGeneral ClassificationOn Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, gene…
Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
The success of deep learning relies on the availability of large-scale annotated data sets, the acquisition of which can be costly, requiring expert domain knowledge. Semi-supervised learning (SSL) mitigates this challen…