secml: Secure and explainable machine learning in Python

We present 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...

Full description

Saved in:
Bibliographic Details
Published in:SoftwareX 2022-06, Vol.18, p.101095, Article 101095
Main Authors: Pintor, Maura, Demetrio, Luca, Sotgiu, Angelo, Melis, Marco, Demontis, Ambra, Biggio, Battista
Format: Article
Language:English
Subjects:
Adversarial attacks
Explainability
Machine learning
Python3
Security
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present 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, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. 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 https://github.com/pralab/secml.
ISSN:2352-7110
2352-7110
DOI:10.1016/j.softx.2022.101095