Enhancing Adversarial Robustness of Deep Neural Networks
  • Release Date : 20 September 2021
  • Publisher : Unknown
  • Genre : Uncategorized
  • Pages : 58 pages
  • ISBN 13 : OCLC:1127291827
Ratings: 4
From 235 Voters
Get This Book

Download or read book entitled Enhancing Adversarial Robustness of Deep Neural Networks by author: Jeffrey Zhang (M. Eng.) which was release on 20 September 2021 and published by Unknown with total page 58 pages . This book available in PDF, EPUB and Kindle Format. Logit-based regularization and pretrain-then-tune are two approaches that have recently been shown to enhance adversarial robustness of machine learning models. In the realm of regularization, Zhang et al. (2019) proposed TRADES, a logit-based regularization optimization function that has been shown to improve upon the robust optimization framework developed by Madry et al. (2018) [14, 9]. They were able to achieve state-of-the-art adversarial accuracy on CIFAR10. In the realm of pretrain- then-tune models, Hendrycks el al. (2019) demonstrated that adversarially pretraining a model on ImageNet then adversarially tuning on CIFAR10 greatly improves the adversarial robustness of machine learning models. In this work, we propose Adversarial Regularization, another logit-based regularization optimization framework that surpasses TRADES in adversarial generalization. Furthermore, we explore the impact of trying different types of adversarial training on the pretrain-then-tune paradigm.

Advances in Visual Computing

Advances in Visual Computing

Author : George Bebis,Zhaozheng Yin,Edward Kim,Jan Bender,Kartic Subr,Bum Chul Kwon,Jian Zhao,Denis Kalkofen,George Baciu
Publisher : Springer Nature
Genre : Computers
Get Book