Skip to content

PyTorch Implementation of Generating Adversarial Images using Various Attacks

Notifications You must be signed in to change notification settings

aamir-mustafa/generate-adv-examples

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 

Repository files navigation

generate-adv-examples

This repository is a PyTorch Implementation of generating adversarial images using various types of attacks schemes.

Figure 1

Clone the repository

Clone this repository into any place you want.

git clone https://github.com/aamir-mustafa/generate-adv-examples
cd generate-adv-examples

Download the NIPS 2017 Adversarial Learning Development Dataset comprising of 1000 ImageNet alike images of size 299 x 299. Kaggle Link. Download the file images.zip to the directory.

Generate and Save Adversarial Examples

Use the following python file to generate and save the adversarial examples against various ImageNet pre-trained models. We provide implementations for four types of attacks : FGSM, BIM, MIM, PGD

generate.py

About

PyTorch Implementation of Generating Adversarial Images using Various Attacks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages