Hyperparticle/one-pixel-attack-keras

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

50
/ 100
Established

This project explores how a deep neural network can be fooled into misclassifying an image by changing just one pixel. It takes an image and a target misclassification, then outputs a slightly altered image that causes the network to make the wrong prediction. This is for machine learning researchers and security analysts evaluating the robustness of image classification models.

1,232 stars. No commits in the last 6 months.

Use this if you need to understand the vulnerability of deep neural networks to minimal adversarial perturbations in image classification tasks.

Not ideal if you are looking for a general-purpose image augmentation or data anonymization tool.

adversarial-machine-learning image-classification-security deep-learning-vulnerability model-robustness computer-vision-security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,232

Forks

215

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Hyperparticle/one-pixel-attack-keras"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.