AdvSecureNet: A Python Toolkit for Adversarial Machine Learning
This provides researchers and practitioners with a more versatile and reproducible toolkit for studying adversarial vulnerabilities in machine learning models, though it is incremental as it builds on existing tool concepts.
The authors tackled the problem of limited features and flexibility in existing adversarial machine learning tools by introducing AdvSecureNet, a PyTorch-based toolkit that is the first to natively support multi-GPU setups for attacks, defenses, and evaluation, and includes CLI/API interfaces with YAML configuration.
Machine learning models are vulnerable to adversarial attacks. Several tools have been developed to research these vulnerabilities, but they often lack comprehensive features and flexibility. We introduce AdvSecureNet, a PyTorch based toolkit for adversarial machine learning that is the first to natively support multi-GPU setups for attacks, defenses, and evaluation. It is the first toolkit that supports both CLI and API interfaces and external YAML configuration files to enhance versatility and reproducibility. The toolkit includes multiple attacks, defenses and evaluation metrics. Rigiorous software engineering practices are followed to ensure high code quality and maintainability. The project is available as an open-source project on GitHub at https://github.com/melihcatal/advsecurenet and installable via PyPI.