Machine Learning (ML) is a field within Artificial Intelligence (AI) that focuses on the ability of computers to learn on their own without being programmed. When these systems are misled or given malicious inputs, Adversarial Machine Learning (AML) has likely been employed. AML is conducted by malicious actors to undermine the capabilities of ML; whereas, ML security focuses on understanding these attack consequences with the intention to mitigate the effects of malicious actors.
NISTIR 8269, A Taxonomy and Terminology of Adversarial Machine Learning was developed as a step toward securing applications of AI, specifically AML, and features a taxonomy of concepts and terminologies. This NISTIR can inform future standards and best practices for assessing and managing ML security by establishing a common language and understanding of the rapidly developing AML landscape.