Please use this identifier to cite or link to this item: https://dair.nps.edu/handle/123456789/4453
Title: Interdependence Analysis for Artificial Intelligence System Safety
Authors: Bruce Nagy
Scot Miller
Keywords: Interdependence Analysis
Artificial Intelligence
System Safety
Issue Date: 20-May-2021
Publisher: Acquisition Research Program
Citation: Published--Unlimited Distribution
Series/Report no.: Acquisition Management;SYM-AM-21-146
Abstract: Engineers responsible for evaluating tactical and weapons systems for system safety will need a new approach for evaluating emerging artificial intelligence (AI)-enabled systems, since these systems leverage machine learning (ML) techniques. For many reasons, ML algorithms are often difficult to diagnose for safety purposes. For instance, they did not lend themselves easily to codebase inspections, thus necessitating the reduction in “autonomy” of the ML-enabled component. By modifying Interdependence Analysis (IA) techniques, a more rigorous approach to evaluating AI/ML-enabled weapons can be found. The IA process produces a rigorous exploration based on observability, predictability, and direct ability, highlighting the key requirements that encapsulate all interactions between human and machine. This paper explores using IA to define the interaction requirements for human–machine teaming, employs those results to identify key critical functions, and leverages those findings to reveal how “autonomy” reduction might be employed.
Description: Acquisition Management / Defense Acquisition Community Contributor
URI: https://dair.nps.edu/handle/123456789/4453
Appears in Collections:Annual Acquisition Research Symposium Proceedings & Presentations

Files in This Item:
File Description SizeFormat 
SYM-AM-21-146.pdfPresentation PDF895.2 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.