NTRS - NASA Technical Reports Server

Back to Results
Hazard Contribution Modes of Machine Learning ComponentsAmongst the essential steps to be taken towards developing and deploying safe systems with embedded learning-enabled components (LECs) i.e., software components that use ma- chine learning (ML)—are to analyze and understand the con- tribution of the constituent LECs to safety, and to assure that those contributions have been appropriately managed. This paper addresses both steps by, first, introducing the notion of hazard contribution modes (HCMs) a categorization of the ways in which the ML elements of LECs can contribute to hazardous system states; and, second, describing how argumentation patterns can capture the reasoning that can be used to assure HCM mitigation. Our framework is generic in the sense that the categories of HCMs developed i) can admit different learning schemes, i.e., supervised, unsupervised, and reinforcement learning, and ii) are not dependent on the type of system in which the LECs are embedded, i.e., both cyber and cyber-physical systems. One of the goals of this work is to serve a starting point for systematizing L analysis towards eventually automating it in a tool.

Document ID
Document Type
Conference Paper
Smith, Colin
(Oak Ridge National Lab. TN, United States)
Denney, Ewen
(KBRwyle Moffett Field, CA, United States)
Pai, Ganeshmadhav J.
(KBRwyle Moffett Field, CA, United States)
Date Acquired
March 20, 2020
Publication Date
February 7, 2020
Subject Category
Mathematical And Computer Sciences (General)
Report/Patent Number
Meeting Information
Meeting: AAAI Conference on Artificial Intelligence
Location: New York, NY
Country: United States
Start Date: February 7, 2020
End Date: February 12, 2020
Sponsors: Association for the Advancement of Artificial Intelligence (AAAI)
Funding Number(s)
Distribution Limits
Public Use Permitted.
No Preview Available