2019/11/03 by Erik Blasch, Blasch, Erik, James Sung +7
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Computers and Society (cs.CY) #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Information Retrieval (cs.IR) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.05727
openalex publication_date 2019/11/03 · openalex created_date 2019/11/22 · openalex updated_date 2026/07/28
Recent advances in artificial intelligence (AI) have lead to an explosion of multimedia applications (e.g., computer vision (CV) and natural language processing (NLP)) for different domains such as commercial, industrial, and intelligence. In particular, the use of AI applications in a national security environment is often problematic because the opaque nature of the systems leads to an inability for a human to understand how the results came about. A reliance on 'black boxes' to generate predictions and inform decisions is potentially disastrous. This paper explores how the application of standards during each stage of the development of an AI system deployed and used in a national security environment would help enable trust. Specifically, we focus on the standards outlined in Intelligence Community Directive 203 (Analytic Standards) to subject machine outputs to the same rigorous standards as analysis performed by humans.