Must-read Papers on Textual Adversarial Attack and Defense

auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs

Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

This repository contains the implementation of three adversarial example attack methods FGSM, IFGSM, MI-FGSM and one Distillation as defense against all attacks using MNIST dataset.

A curated list of papers on adversarial machine learning (adversarial examples and defense methods).

This is the course project for CSCE585: ML Systems. Students will build their machine learning systems based on the provided infrastructure --- Athena.

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

Source Code for 'SECurity evaluation platform FOR Speaker Recognition' released in 'Defending against Audio Adversarial Examples on Speaker Recognition Systems'

pytorch implementation of Parametric Noise Injection for adversarial defense

Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTorch).

Adversarial attacks on Deep Reinforcement Learning (RL)

A list of awesome resources for adversarial attack and defense method in deep learning

😎 A curated list of awesome real-world adversarial examples resources

Adversarial Distributional Training (NeurIPS 2020)

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Feature Separation and Recalibration (CVPR 2023 Highlights)

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

LSA : Layer Sustainability Analysis framework for the analysis of layer vulnerability in a given neural network. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis.

Adversarial Ranking Attack and Defense, ECCV, 2020.

Adversarial detection and defense for deep learning systems using robust feature alignment