paper-with-me

Papers

Adversarially Robust Training through Structured Gradient Regularization

2018-05-22 · Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann

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.

📄 PDF Abstract BibTeX arXiv:1805.08736

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scaleable input gradient regularization for adversarial robustness

2019-05-27 · Chris Finlay, Adam M. Oberman

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 Robustness

Lipschitz regularized Deep Neural Networks generalize and are adversarially robust

2018-08-28 · Chris Finlay, Jeff Calder, Bilal Abbasi, Adam Oberman

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 Robustness

Starfire: Regularization-Free Adversarially-Robust Structured Sparse Training

2019-09-25 · Noah Gamboa, Kais Kudrolli, Anand Dhoot, Ardavan Pedram

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

2024-12-17 · Dongya Wu, Xin Li

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 Attack

Adversarially robust segmentation models learn perceptually-aligned gradients

2022-04-03 · Pedro Sandoval-Segura

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