A Survey on Methods for the Safety Assurance of Machine Learning Based Systems
Faculty/Professorship: | Cognitive Systems |
Author(s): | Schwalbe, Gesina ![]() |
Corporate Body: | European Congress on Embedded Real Time Software and Systems (ERTS), 10, 2020, Toulouse |
Publisher Information: | Bamberg : Otto-Friedrich-Universität |
Year of publication: | 2020 |
Pages: | 11 |
Source/Other editions: | European Congress on Embedded Real Time Software and Systems (ERTS) / European Congress on Embedded Real Time Software and Systems (ERTS) (Hg.) – Toulouse : ERTS, 2020, S. 11 |
Language(s): | English |
DOI: | 10.20378/irb-47275 |
Licence: | Creative Commons - CC BY-NC-SA - Attribution - NonCommercial - ShareAlike 4.0 International |
URN: | urn:nbn:de:bvb:473-irb-472752 |
Abstract: | Methods for safety assurance suggested by the ISO 26262 automotive functional safety standard are not sufficient for applications based on machine learning (ML). We provide a structured, certification oriented overview on available methods supporting the safety argumen-tation of a ML based system. It is sorted into life-cycle phases, and maturity of the approach as well as applicability to different ML types are collected. From this we deduce current open challenges: powerful solvers, inclusion of expert knowledge, validation of data representativity and model diversity, and model introspection with provable guarantees. |
GND Keywords: | ISO/DIS 26262; Funktionssicherheit; Maschinelles Lernen; Künstliche Intelligenz |
Keywords: | functional safety, life-cycle, ISO 26262, machine learning, explainable AI |
DDC Classification: | 004 Computer science |
RVK Classification: | ST 300 |
Peer Reviewed: | Ja |
International Distribution: | Ja |
Open Access Journal: | Ja |
Type: | Conferenceobject |
URI: | https://fis.uni-bamberg.de/handle/uniba/47275 |
Release Date: | 3. July 2020 |
File | Description | Size | Format | |
---|---|---|---|---|
fisba47275.pdf | 305.69 kB | View/Open |

originated at the
University of Bamberg
University of Bamberg