pralab/secml

A Python library for Secure and Explainable Machine Learning

54
/ 100
Established

SecML helps data scientists and machine learning engineers assess how robust their AI models are against malicious attacks. You input your trained machine learning model and a dataset, and it shows you how easily an attacker could trick your model or inject bad data. This allows you to understand and improve your model's security before deployment.

191 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to evaluate the security of your machine learning models against adversarial attempts to fool or corrupt them.

Not ideal if you are looking for a general-purpose machine learning library for building and training models from scratch, as its focus is on security evaluation.

AI-security adversarial-machine-learning model-robustness data-integrity threat-modeling
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

191

Forks

27

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jun 23, 2025

Commits (30d)

0

Dependencies

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pralab/secml"

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