AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack
This provides a tool for researchers and practitioners to assess ML security, but it is incremental as it aggregates existing methods into a library.
The authors tackled the problem of evaluating machine learning security under adversarial attacks by developing AdversariaLib, an open-source Python library that supports multiple attacks, ML algorithms, and platforms, with optimized C/C++ implementations for fast evaluation.
We present AdversariaLib, an open-source python library for the security evaluation of machine learning (ML) against carefully-targeted attacks. It supports the implementation of several attacks proposed thus far in the literature of adversarial learning, allows for the evaluation of a wide range of ML algorithms, runs on multiple platforms, and has multi-processing enabled. The library has a modular architecture that makes it easy to use and to extend by implementing novel attacks and countermeasures. It relies on other widely-used open-source ML libraries, including scikit-learn and FANN. Classification algorithms are implemented and optimized in C/C++, allowing for a fast evaluation of the simulated attacks. The package is distributed under the GNU General Public License v3, and it is available for download at http://sourceforge.net/projects/adversarialib.