Adversarial Machine Learning

synthesizing_robust_adversarial

PyTorch implementation of Expectation over Transformation

SpectralDef_Framework

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

multiLID

vp-for-adversarial-robustness

Visual Prompting for Adversarial Robustness

AdvOpenOOD

auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

BlackboxBench

SpectralDefense

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

AdversarialAttacks

adversarialattackspytorch

PyTorch implementation of adversarial attacks.

backdoor-toolbox

A compact toolbox for backdoor attacks and defenses.

CLIP

Contrastive Language-Image Pretraining

competence_estimation

cutmix

a Ready-to-use PyTorch Extension of Unofficial CutMix Implementations with more improved performance.

denoising-diffusion-flax

Implementing the Denoising Diffusion Probabilistic Model in Flax

DiffAttack

An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.

DiffPure

A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.

evaluating-adaptive-test-time-defenses

fast-DiT

Improved PyTorch Implementation of "Scalable Diffusion Models with Transformers"

foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

GuidedDiffusionPur

MALT

MALT is a attack method utilizing pre-attack targeting method to speed up and improve the state of the art AutoAttack. Fully presented in the paper. the paper

pytorch-ddpm-cifar10

Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

robust-ood-detection

Robust Out-of-distribution Detection in Neural Networks

robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

tf_to_pytorch_model

Convert tensorflow model to pytorch model via [MMdnn](https://github.com/microsoft/MMdnn) for adversarial attacks.

TRADES

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

vim

Official repository for CVPR2022 publication, ViM: Out-Of-Distribution with Virtual-logit Matching

visual_prompting

Exploring Visual Prompts for Adapting Large-Scale Models