fgsm

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.

Implementation of Papers on Adversarial Examples

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

Detection by Attack: Detecting Adversarial Samples by Undercover Attack

Tensorflow Implementation of Adversarial Attack to Capsule Networks

PyTorch library for adversarial attack and training

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

The first real-world adversarial attack on MTCNN face detetction system to date

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.

Implementation of gradient-based adversarial attack(FGSM,MI-FGSM,PGD)

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Implementation of adversarial training under fast-gradient sign method (FGSM), projected gradient descent (PGD) and CW using Wide-ResNet-28-10 on cifar-10. Sample code is re-usable despite changing the model or dataset.

Reproduce multiple adversarial attack methods

implement Kervolutional Neural Networks (CVPR, 2019) and compare with CNN under the white box attack

六代兴亡如梦，苒苒惊时月。纵使岁寒途远，此志应难夺。

using adversarial attacks to confuse deep-chicken-terminator 🛡️ 🐔

Adversarial Attack on 3D U-Net model: Brain Tumour Segmentation.

Fast Gradient Sign Method for Adversarial Attack (PyTorch)

Detection of network traffic anomalies using unsupervised machine learning

FGSM attack Pytorch module for semantic segmentation networks, with examples provided for Deeplab V3.

This project tests multiple different machine learning algorithms that can detect adversarial attacks in multi-agent reinforcement learning settings. Baselines were used to compare performance of a proposed ensemble model. Then, using FGSM, we re-attacked the ensemble detection model with perturbed observations. Read more at the pdf titled FinalPaper.

Implementation of FGSM (Fast Gradient Sign Method) attack on fine-tuned MobileNet architecture trained for flood detection in images.

Package for adversarial attack in pytorch

Repository consists of pre-trained CNN model in pytorch, hitting 89% on Fashion MNIST dataset. Adversarial attack was implemented on a given model. Results are below.

Implementing white box adversarial attacks on parameters and architecture of CNN in PyTorch

Adversarial Attack using a DCGAN

WideResNet implementation on MNIST dataset. FGSM and PGD adversarial attacks on standard training, PGD adversarial training, and Feature Scattering adversarial training.

PCA , CNN, FGSM using MNIST