TY - CPAPER TI - A Survey on Methods for the Safety Assurance of Machine Learning Based Systems AU - Schwalbe, Gesina AU - Schels, Martin PY - 2020 T2 - Proceeding of the 10th European Congress on Embedded Real Time Software and Systems CY - Toulouse UR - https://fis.uni-bamberg.de/handle/uniba/47326 LA - eng AB - 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. KW - functional safety KW - life-cycle KW - ISO 26262 KW - machine learning KW - explainable AI ER -