Adversarially Robust Training through Structured Gradient Regularization
We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived as a controlled approximation from first principles, leveraging the fundamental link between training with noise and regularization. It adds very little computational overhead during learning and is simple to implement generically in standard deep learning frameworks. Our experiments provide strong evidence that structured gradient regularization can act as an effective first line of defense against attacks based on low-level signal corruption.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Scaleable input gradient regularization for adversarial robustness
In this work we revisit gradient regularization for adversarial robustness with some new ingredients. First, we derive new per-image theoretical robustness bounds based on local gradient information. These bounds strongl…
Adversarial AttackAdversarial DefenseAdversarial RobustnessLipschitz 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 RobustnessStarfire: Regularization-Free Adversarially-Robust Structured Sparse Training
This paper studies structured sparse training of CNNs with a gradual pruning technique that leads to fixed, sparse weight matrices after a set number of epochs. We simplify the structure of the enforced sparsity so that …
Adversarially robust generalization theory via Jacobian regularization for deep neural networks
Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abu…
Adversarial AttackAdversarially robust segmentation models learn perceptually-aligned gradients
The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, w…
Image GenerationImage InpaintingSegmentationSemantic Segmentation