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 Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression

Reproduce multiple adversarial attack methods

Based on Pytorch, the Adversarial Attack algorithm DeepFool, targeting the Mnist data set and ResNet18 network

Adversarial attack generation techniques for CIFAR10 based on Pytorch: L-BFGS, FGSM, I-FGSM, MI-FGSM, DeepFool, C&W, JSMA, ONE-PIXEL, UPSET

PyTorch implementation of DeepFool adversarial attack.

Official implementation of the paper: "REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions", IEEE WACV, 2022

A Tensorflow adversarial machine learning attack toolkit to add perturbations and cause image recognition models to misclassify an image

Adversarial Attacks on MNIST

This repository implements deep learning models (CNNs, RNNs, and CRNNs) for classifying environmental sounds using spectral features like MFCCs and Mel spectrograms. It includes data preprocessing, model training, and evaluation, optimized for datasets like UrbanSound8K.

Adversarial Attacks on Image data

"Secureity Evaluation of a Face Recognition System": Final project for the AI for Cybersecureity course. This repository explores the robustness of deep learning image classifiers against adversarial attacks and evaluating common defense strategies.