Code Monkey home page Code Monkey logo

advgan_pytorch's Introduction

advGAN_pytorch

a Pytorch implementation of the paper "Generating Adversarial Examples with Adversarial Networks" (advGAN).

training the target model

python3 train_target_model.py

training the advGAN

python3 main.py

testing adversarial examples

python3 test_adversarial_examples.py

results

attack success rate in the MNIST test set: 99%

NOTE: My implementation is a little different from the paper, because I add a clipping trick.

advgan_pytorch's People

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

qiushilin sunshine352 chenbch duoergun0729 syk1993 baogiadoan fyang623 johnsonkee xuwenting vitvicky minusome byerhu ruipengz tinemar tianqi-777 polly2014 qiuweimin1332499 tangjunjun0925 gynancy qianrenjian harrywuhust2022 forlovezed maryamshahpasand anshukun akolada dwtrott scintillare t27 ismeyueyue lijjcq biiigerrr xinyuefly86 bngabonziza xaddwell venkatsubramanyam ideasplus dongchengdonghangzhou souvikpaul01 zlwangustc tengfei-zju zouyayi ckichen hydqiu luning409 repo-collection yiminglii karma3983 daisybob naihao rhaldarpurdue pinkbag-711 191578010 yangyzju ambigev dagrons liudengbocode amrakibulhasan loserlulin9 five-six-seven lucasticc gcxamy ananchampion utricularor saigontrade88

advgan_pytorch's Issues

How to test madrylab's defense methods?

https://github.com/MadryLab/mnist_challenge

Hello, I am trying to attack MadryLab's defense strategy with your project （advGAN）. However, it did not get the 92.76% effect mentioned in the article （Generating Adversarial Examples with Adversarial Networks）. Since I just started this research work, I don't know whether it is the problem of parameter setting or the wrong operations.

Generator loss doesn't converge

Basically, I love your idea but I found that the loss of generator doesn't converge
but increase with iteration.

Sincerely, kevin

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.