paper-with-me

Papers

Improving the affordability of robustness training for DNNs

2020-02-11 · Sidharth Gupta, Parijat Dube, Ashish Verma

Projected Gradient Descent (PGD) based adversarial training has become one of the most prominent methods for building robust deep neural network models. However, the computational complexity associated with this approach, due to the maximization of the loss function when finding adversaries, is a longstanding problem and may be prohibitive when using larger and more complex models. In this paper we show that the initial phase of adversarial training is redundant and can be replaced with natural training which significantly improves the computational efficiency. We demonstrate that this efficiency gain can be achieved without any loss in accuracy on natural and adversarial test samples. We support our argument with insights on the nature of the adversaries and their relative strength during the training process. We show that our proposed method can reduce the training time by a factor of up to 2.5 with comparable or better model test accuracy and generalization on various strengths of adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2002.04237

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network

2022-07-07 · SeongJin Park, Haedong Jeong, Giyoung Jeon, Jaesik Choi

In general, Deep Neural Networks (DNNs) are evaluated by the generalization performance measured on unseen data excluded from the training phase. Along with the development of DNNs, the generalization performance converg…

Adversarial AttackAdversarial Robustness

AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion

2023-01-01 · CVPR 2023 1 · Shenglin Yin, Kelu Yao, Sheng Shi, Yangzhou Du 외

The deep neural networks (DNNs) trained by adversarial training (AT) usually suffered from significant robust generalization gap, i.e., DNNs achieve high training robustness but low test robustness. In this paper, we…

Diversity

Empirical Study of the Decision Region and Robustness in Deep Neural Networks

2021-09-29 · SeongJin Park, Haedong Jeong, Giyoung Jeon, Jaesik Choi

In general, the Deep Neural Networks (DNNs) is evaluated by the generalization performance measured on the unseen data excluded from the training phase. Along with the development of DNNs, the generalization performance …

Adversarial AttackAdversarial Robustness

Scalable Differential Privacy with Certified Robustness in Adversarial Learning

2020-01-01 · ICML 2020 1 · Hai Phan, My T. Thai, Han Hu, Ruoming Jin 외

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the se…

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

2021-10-07 · NeurIPS 2021 12 · Hanxun Huang, Yisen Wang, Sarah Monazam Erfani, Quanquan Gu 외

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversarial training has demonstrated promising…

Adversarial Robustness