# secml: A Python Library for Secure and Explainable Machine Learning

arXiv: https://arxiv.org/abs/1912.10013 · HTML: https://mlsanity.com/paper/1912.10013/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [The Threat of Offensive AI to Organizations](https://mlsanity.com/paper/2106.15764/) (2021)
- [Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples](https://mlsanity.com/paper/2106.09947/) (2021)
- [Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness](https://mlsanity.com/paper/2403.14641/) (2024)
- [Combining Machine Learning Defenses without Conflicts](https://mlsanity.com/paper/2411.09776/) (2024)
- [Bridging Ethical Principles and Algorithmic Methods: An Alternative Approach for Assessing Trustworthiness in AI Systems](https://mlsanity.com/paper/2506.22774/) (2025)
- [Hyperparameter Tuning Through Pessimistic Bilevel Optimization](https://mlsanity.com/paper/2412.03666/) (2024)

## Abstract (arXiv)

We present textttsecml, 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, textttsecml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. textttsecml 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 urlhttps://github.com/pralab/secml.