Concept Enforcement and Modularization as Methods for the ISO 26262 Safety Argumentation of Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Concept Enforcement and Modularization as Methods for the ISO 26262 Safety Argumentation of Neural Networks

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.
Fichier principal
Vignette du fichier
ERTS2020_paper_10.pdf (857.36 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02442796 , version 1 (16-01-2020)

Identifiers

  • HAL Id : hal-02442796 , version 1

Cite

Gesina Schwalbe, Martin Schels. Concept Enforcement and Modularization as Methods for the ISO 26262 Safety Argumentation of Neural Networks. 10th European Congress on Embedded Real Time Software and Systems (ERTS 2020), Jan 2020, Toulouse, France. ⟨hal-02442796⟩

Collections

ERTS2020
481 View
262 Download

Share

Gmail Mastodon Facebook X LinkedIn More