Defensegan

Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)

Features

Security and Privacy - Protects classifiers against adversarial attacks using generative priors.

RP-GAN: Stable GAN Training with Random Projections

Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · R. Huang

A repository for the paper "Improved Adversarial Systems for 3D Object Generation and Reconstruction".

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

RP-GAN: Stable GAN Training with Random Projections

Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · R. Huang

A repository for the paper "Improved Adversarial Systems for 3D Object Generation and Reconstruction".

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning