Back to Search Start Over

advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch

Authors :
Ding, Gavin Weiguang
Wang, Luyu
Jin, Xiaomeng
Publication Year :
2019

Abstract

advertorch is a toolbox for adversarial robustness research. It contains various implementations for attacks, defenses and robust training methods. advertorch is built on PyTorch (Paszke et al., 2017), and leverages the advantages of the dynamic computational graph to provide concise and efficient reference implementations. The code is licensed under the LGPL license and is open sourced at https://github.com/BorealisAI/advertorch .

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1902.07623
Document Type :
Working Paper