@inproceedings{schwalbe2020_47860,
  title = {Concept Enforcement and Modularization as Methods for the ISO 26262 Safety Argumentation of Neural Networks},
  author = {Schwalbe, Gesina and Schels, Martin},
  year = {2020},
  booktitle = {Proceeding of the 10th European Congress on Embedded Real Time Software and Systems},
  pages = {1-10},
  address = {Toulouse},
  url = {https://fis.uni-bamberg.de/handle/uniba/47860},
  language = {eng},
  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.},
  keywords = {concept enforcement, machine learning, neural networks, functional safety, ISO 26262, goal structuring notation, explainable AI}
}
