Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy

• Published in: arXiv.org
• Main Authors: Kawamoto, Yusuke, Miyake, Kazumasa, Konishi, Koichi, Oiwa, Yutaka
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 19.01.2023
• Subjects: Artificial intelligence; Classification; Literature reviews; Machine learning; Security; Taxonomy

In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems. We first classify the damage caused by attacks against ML-based systems, define ML-specific security, and discuss its characteristics. Next, we enumerate all relevant assets and stakeholders and provide a general taxonomy for ML-specific threats. Then, we collect a wide range of security controls against ML-specific threats through an extensive review of recent literature. Finally, we classify the vulnerabilities and controls of an ML-based system in terms of each vulnerable asset in the system's entire lifecycle.