SecML (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 team in the past years.

It comes with a set of powerful features:

• Dense/Sparse data support. We provide full, transparent support for both dense (through numpy library) and sparse data (through scipy library) in a single data structure.

• Wide range of supported ML algorithms. All supervised learning algorithms supported by scikit-learn are available, as well as Neural Networks (NNs) through PyTorch deep learning platform (coming soon).

• Built-in attack algorithms. Evasion and poisoning attacks based on a custom-developed fast solver.

• Visualize your results. We provide visualization and plotting framework based on the widely-known library matplotlib.

• Explain your results. Explainable ML methods to interpret model decisions via influential features and prototypes. (coming soon)

• Extensible. Easily create new wrappers for ML models or attack algorithms extending our abstract interfaces.

• Multi-processing. Do you want to save time further? We provide full compatibility with all the multi-processing features of scikit-learn and pytorch, along with built-in support of the joblib library.

Authors