secml: A Python Library for Secure and Explainable Machine Learning

Authors: Maura Pintor, Luca Demetrio, Angelo Sotgiu, Marco Melis, Ambra Demontis, Battista Biggio
Published: 2019-12-20 | Updated: 2022-05-13

Source: https://arxiv.org/abs/1912.10013

PDF: https://arxiv.org/pdf/1912.10013

AIにより推定されたラベル

ポイズニング 敵対的学習 透かし評価

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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.