Adversarial Machine Learning

adversarial-detection

Code and experiments for the adversarial detection paper

AdvOpenOOD

arxiv_crawler

auto-attack

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

bib_adversarial_examples

Literature collection of adversarial examples.

BlackboxBench

multiLID

SpectralDef_Framework

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

synthesizing_robust_adversarial

PyTorch implementation of Expectation over Transformation

vp-for-adversarial-robustness

Visual Prompting for Adversarial Robustness

adverML/synthesizing_robust_adversarial

PyTorch implementation of Expectation over Transformation

adverML/SpectralDef_Framework

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

adverML/multiLID

adverML/vp-for-adversarial-robustness

Visual Prompting for Adversarial Robustness

adverML/AdvOpenOOD

adverML/auto-attack

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

adverML/BlackboxBench

adverML/SpectralDefense

adverML/denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

adverML/AdversarialAttacks

adverML/adversarialattackspytorch

PyTorch implementation of adversarial attacks.

adverML/backdoor-toolbox

A compact toolbox for backdoor attacks and defenses.

adverML/CLIP

Contrastive Language-Image Pretraining

adverML/competence_estimation

adverML/cutmix

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

adverML/denoising-diffusion-flax

Implementing the Denoising Diffusion Probabilistic Model in Flax

adverML/DiffAttack

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

adverML/DiffPure

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

adverML/evaluating-adaptive-test-time-defenses

adverML/fast-DiT

Improved PyTorch Implementation of "Scalable Diffusion Models with Transformers"

adverML/foolbox

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

adverML/GuidedDiffusionPur

adverML/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

adverML/pytorch-ddpm-cifar10

Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

adverML/robust-ood-detection

Robust Out-of-distribution Detection in Neural Networks

adverML/robustness

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

adverML/tf_to_pytorch_model

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

adverML/TRADES

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

adverML/vim

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

adverML/visual_prompting

Exploring Visual Prompts for Adapting Large-Scale Models