Harry24k/FGSM-pytorch
A pytorch implementation of "Explaining and harnessing adversarial examples"
This project helps machine learning engineers or researchers understand how to make small, imperceptible changes to an image that cause a deep learning model to misclassify it. It takes an input image and a pre-trained image classification model (like Inception v3), and outputs an "adversarial" image designed to trick the model. The primary users are those working on the security and robustness of AI models.
No commits in the last 6 months.
Use this if you are a machine learning practitioner experimenting with adversarial attacks to test the vulnerability of your image classification models.
Not ideal if you are looking for a comprehensive toolkit for various adversarial attack methods or a maintained library for model defense strategies.
Stars
70
Forks
16
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Harry24k/FGSM-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Trusted-AI/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion,...
bethgelab/foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research