Definitions

In this Act: (1) Adversarial robustness The term adversarial robustness means the degree to which an artificial intelligence model is able to resist attacks that would induce it to produce incorrect, restricted, or harmful outputs, while maintaining integrity, reliability, and privacy. (2) Artificial intelligence The term artificial intelligence has the meaning given the term in section 5002 of the National Artificial Intelligence Initiative Act of 2020 (15 U.S.C. 9401). (3) Interpretability The term interpretability means the degree to which humans are able to accurately understand how an artificial intelligence model makes decisions and considers inputs and how the outputs or behaviors of the model respond to a change in the inputs. (4) Red-teaming The term red-teaming means a structured, interactive, and adversarial process to test an artificial intelligence system by simulating real-world actions to find vulnerabilities or flaws in the system. (5) Secretary The term Secretary means the Secretary of Homeland Security.