secml: A Python Library for Secure and Explainable Machine Learning
arXiv:1912.10013 · doi:10.1016/j.softx.2022.101095
Abstract
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples against deep neural networks and training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and the corresponding defenses under both white-box and black-box threat models. To this end, \texttt{secml} provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. \texttt{secml} also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0 and hosted at \url{https://github.com/pralab/secml}.
arXiv commentAccepted for publication to SoftwareX. Published version can be found at: https://doi.org/10.1016/j.softx.2022.101095
References in corpus (8)
- Intriguing properties of neural networks
- Axiomatic Attribution for Deep Networks
- Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
- Understanding Black-box Predictions via Influence Functions
- Poisoning Attacks against Support Vector Machines
- Stealing Machine Learning Models via Prediction APIs
- Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
- Foolbox: A Python toolbox to benchmark the robustness of machine learning models