is an open-source python library for the security evaluation
of machine learning (ML)-based classifiers under adversarial
attacks. It comes with a set of powerful features:
not least, AdversariaLib is free software,
released under the GNU GPL version 3!
Running sophisticated experiments is as easy as launching
a single script. Experimental settings can be defined
through a single setup file.
range of supported ML algorithms. All
supervised learning algorithms supported by scikit-learn
are available, as well as Neural Networks (NNs), by means
of our scikit-learn wrapper for FANN. In the current
implementation, the library allows for the security
evaluation of SVMs with linear, rbf, and polynomial
kernels, and NNs with one hidden layer, against evasion
Learning and Evaluation. Thanks to scikit-learn
and FANN, all supported ML algorithms are optimized and
written in C/C++ language.
attack algorithms. Evasion attacks based on
Other attack algorithms can be easily added to the
Do you want to further save time? The built-in attack
algorithms can run concurrently on multiple processors.