https://github.com/alvinwan/tricking-neural-networks

Fooling a neural network with adversarial examples
https://github.com/alvinwan/tricking-neural-networks

adversarial-example adversarial-machine-learning deep-learning tutorial

Last synced: about 1 month ago
JSON representation

Fooling a neural network with adversarial examples

• Host: GitHub
• URL: https://github.com/alvinwan/tricking-neural-networks
• Owner: alvinwan
• License: mit
• Created: 2020-06-08T08:25:21.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-06-22T02:15:27.000Z (over 2 years ago)
• Last Synced: 2023-02-27T17:32:58.424Z (over 1 year ago)
• Topics: adversarial-example, adversarial-machine-learning, deep-learning, tutorial
• Language: Python
• Size: 769 KB
• Stars: 3
• Watchers: 2
• Forks: 2
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# How to Trick a Neural Network

Fooling a neural network with adversarial examples. This repository includes all source code for the tutorial on DigitalOcean with the same title, including:

- adversarial example of corgi that an neural network thinks is a goldfish

- utility to trick any neural network into predicting one class as another

- utility to run an ImageNet-pretrained ResNet18 neural network on any image of your choosing

created by [Alvin Wan](http://alvinwan.com), June 2020