Proposed V-Model for Verification, Validation, and Safety Activities for Artificial Intelligence

Abstract

The Department of Defense strives to continuously develop and acquire systems that utilize novel technologies and methods for implementing new and complex mission requirements. One of the identified technologies with high impact and benefit to the Warfighter is the integration of Artificial Intelligence (AI) and Machine Learning (ML). Current AI models and methods have added layers of complexity to achieving a satisfactory level of verification and validation (V&V), possibly resulting in elevated risks with fewer mitigations. Regardless of the type of applications for AI technology within the DoD, the technology implementation must be verified, validated, and ultimately any residual risks accepted. This paper looks to introduce a V-model concept for Artificial Intelligence and Machine Learning, to include an outline of proposed activities that the development, assurance, and evaluation communities can follow. By following this proposed assessment, these organizations can increase their understanding and knowledge of the system, mitigating risk and helping to achieve justified confidence.