DSE-MSU/DeepRobust

A pytorch adversarial library for attack and defense methods on images and graphs

61
/ 100
Established

This is a library for researchers and developers working with machine learning models that need to be resilient against adversarial attacks. It takes existing image and graph data and applies various attack methods to test model vulnerabilities, or defense strategies to strengthen models. The output helps machine learning engineers and AI security researchers build and evaluate more robust AI systems.

1,080 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a machine learning engineer or AI security researcher needing to evaluate the robustness of your image or graph-based models against malicious attacks, or to implement defense mechanisms.

Not ideal if you are looking for a general machine learning library for model development rather than specific adversarial robustness testing.

AI security adversarial machine learning image classification security graph neural network security model robustness evaluation
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

1,080

Forks

191

Language

Python

License

MIT

Last pushed

Jun 26, 2025

Commits (30d)

0

Dependencies

14

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DSE-MSU/DeepRobust"

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