Secure ML Library

An open-source library for security evaluation of machine learning (ML)-based algorithms

Secure ML Library is an open-source Python library implementing poisoning and evasion attacks against a wide family of learning algorithms, including SVMs, Neural Nets, Random Forests, and other algorithms available from scikit-learn. SecML-Lib also implements some of the secure-learning techniques developed by our lab in the past years.

Stay in touch, SecML-Lib will be released soon!