Secure ML Library
Secure ML: ricerca Tutorial: Wild Patterns Secure ML Library

SecML è stata parzialmente sviluppata grazie ai finanziamenti dell'Unione Europea, Progetto ALOHA, Horizon 2020 Research and Innovation programme, grant agreement N° 780788.

I contenuti di questa pagina sono disponibili prevalentemente in lingua Inglese.
Principali caratteristiche:
-
Dense/Sparse data support. We provide full, transparent support for both dense (through
numpy
library) and sparse data (throughscipy
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
andpytorch
, along with built-in support of the joblib library.

Autori
-
Marco Melis (maintainer) [1]
-
Ambra Demontis [1]
-
Maura Pintor [1], [2]
-
Battista Biggio [1], [2]
Riferimenti
-
numpy
Travis E, Oliphant. “A guide to NumPy”, USA: Trelgol Publishing, 2006. -
scipy
Travis E. Oliphant. “Python for Scientific Computing”, Computing in Science & Engineering, 9, 10-20, 2007. -
scikit-learn
Pedregosa et al., “Scikit-learn: Machine Learning in Python”, JMLR 12, pp. 2825-2830, 2011.
Copyright
SecML è stata sviluppata dal PRALab - Pattern Recognition and Applications lab e da Pluribus One s.r.l. sotto licenza Apache License 2.0. Copyright 2019.
Eventuali bug possono essere segnalati attraverso il GitLab issue tracker.
Ulteriori informazioni in questa pagina.