Concept Enforcement and Modularization as Methods for the ISO 26262 Safety Argumentation of Neural Networks
Year: 2020
Type: other
Abstract: Neural networks (NN) are prone to systematic faults which are hard to detect using the methods recommended by the ISO 26262 automotive functional safety standard. In this paper we propose a unified approach to two methods for NN safety argumentation: Assignment of human interpretable concepts to the internal representation of NNs to enable modularization and formal verification. Feasibility of the required concept embedding analysis is demonstrated in a minimal example and important aspects for generalization are investigated. The contribution of the methods is derived from a proposed generic argumentation structure for a NN model safety case.
DOI: 10.20378/irb-47276
Authors: Gesina Schwalbe, Martin Schels
Institutions: Continental (Germany), University of Bamberg
Language: English
Subfield: Safety, Risk, Reliability and Quality
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W3001927475