An ASR (Automatic Speech Recognition) adversarial attack repository.

vanilla training and adversarial training in PyTorch

Individual Study in Computer Architecture and Systems Laboratory (CASYS) with Prof.Jaehyuk Huh in 2021 Summer

This work is based on enhancing the robustness of targeted classifier models against adversarial attacks. To achieve this, a convolutional autoencoder-based approach is employed that effectively counters adversarial perturbations introduced to the input images.

Evaluating CNN robustness against various adversarial attacks, including FGSM and PGD.

Adversarial Network Attacks (PGD, pixel, FGSM) Noise on MNIST Images Dataset using Python (Pytorch)

A classical or convolutional neural network model with adversarial defense protection

Adversarial Sample Generation

Adversarial attacks on CNN using the FSGM technique.

This repository contains the implementation of three adversarial example attacks including FGSM, noise, semantic attack and a defensive distillation approach to defense against the FGSM attack.

An University Project for the AI4Cybersecurity class.

This study was conducted in collaboration with the University of Prishtina (Kosovo) and the University of Oslo (Norway). This implementation is part of the paper entitled "Attack Analysis of Face Recognition Authentication Systems Using Fast Gradient Sign Method", published in the International Journal of Applied Artificial Intelligence by Taylo…

Adversarial attacks on a deep neural network trained on ImageNet

Implementations for several white-box and black-box attacks.

Learning Adversarial Robustness in Machine Learning both Theory and Practice.

Developed robust image classification models to prevent the effect of adversarial attacks

Adversarial attacks to SRNet

Adversarial Attacks on Image data

Notebook to implement different approaches for Adversarial Attack using Python and PyTorch.

The Fast Gradient Sign Method (FGSM) combines a white box approach with a misclassification goal. It tricks a neural network model into making wrong predictions. We use this technique to anonymize images.