pytorch-cnn-adversarial-attacks

Data augmentation for NLP

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

A Toolbox for Adversarial Robustness Research

An Open-Source Package for Textual Adversarial Attack.

A Harder ImageNet Test Set (CVPR 2021)

Simple pytorch implementation of FGSM and I-FGSM

A non-targeted adversarial attack method, which won the first place in NIPS 2017 non-targeted adversarial attacks competition

Source code for ESORICS 2020 paper "Detection by attack: Detecting adversarial samples by undercover attack"

Official TensorFlow Implementation of Adversarial Training for Free! which trains robust models at no extra cost compared to natural training.

Tensorflow Implementation of Adversarial Attack to Capsule Networks