Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks

Publication

Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks

Schwalbe, Gesina; Schmid, Ute (2020): Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks, Bamberg: Otto-Friedrich-Universität, doi: 10.20378/irb-47277.

Details

Faculty/Chair
Faculty/Professorship
Author
Schwalbe, Gesina
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2020
Pages
6
Source/Other editions
PhD Forum at the European Conference on Machine Learning and Principles of Knowledge Discovery ECML (2019), 6 S.
Year of first publication
2019
Language
English
DOI
Licence
URL
URN
Abstract

The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable concepts as intermediate output of the DNN. Two effects are expected: Requirements can be formulated using these concepts. And the DNN is modularized, thus reduces complexity and therefore easing a safety case. A research project proposal for a PhD thesis is sketched in the following.

GND Keywords
ISO/DIS 26262
Netzwerk
Verifikation
Keywords
ISO 26262
neural networks
formal verification
concept enforcement
DDC Classification
004 Computer science
RVK Classification
ST 300
Type
Workingpaper
URI
Activation date
2020-07-03

Permalink: https://fis.uni-bamberg.de/handle/uniba/47277 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.