Strategies for Safety Goal Decomposition for Neural Networks




Faculty/Professorship: Cognitive Systems  
Author(s): Schwalbe, Gesina ; Schels, Martin
Conference: 3rd ACM Computer Science in Cars Symposium – Future Challenges in Artificial Intelligence & Security for Autonomous Vehicles, Kaiserslautern
Publisher Information: München : German Chapter of the ACM e.V.
Year of publication: 2019
Pages: 3
Language(s): English
Abstract: 
Neural networks (NNs) have become a key technology for solving highly complex tasks, and require integration into future safety argumentations. New safety relevant aspects introduced by NN based algorithms are: representativity of test cases, robustness, inner representation and logic, and failure detection for NNs. In this paper, a general argumentation structure for safety cases respecting these four aspects is proposed together with possible sources of evidence.
GND Keywords: Neuronales Netz ; Beweisführung ; Dekomposition ; Sicherheit
Keywords: neural network, safety argumentation, safety goal decomposition
DDC Classification: 004 Computer science  
RVK Classification: ST 301   
Type: Conferenceobject
URI: https://fis.uni-bamberg.de/handle/uniba/53985
Release Date: 10. May 2022