Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25396
Publication type: Conference paper
Type of review: Peer review (abstract)
Title: Security and safety aspects of AI in industry applications
Authors: Doran, Hans Dermot
et. al: No
DOI: 10.48550/arXiv.2207.10809
10.21256/zhaw-25396
Proceedings: Proceedings of Embedded World Conference 2022
Editors of the parent work: Sikora, Axel
Page(s): 373
Pages to: 378
Conference details: Embedded World Conference, Nuremberg, Germany, 21-23 June 2022
Issue Date: 23-Jun-2022
Publisher / Ed. Institution: WEKA
ISBN: 978-3-645-50194-1
Language: English
Subjects: Safety; Security; Deep learning; Neural network classifier; Functional safety
Subject (DDC): 006: Special computer methods
Abstract: In this relatively informal discussion-paper we summarise issues in the domains of safety and security in machine learning that will affect industry sectors in the next five to ten years. Various products using neural network classification, most often in vision related applications but also in predictive maintenance, have been researched and applied in real-world applications in recent years. Nevertheless, reports of underlying problems in both safety and security related domains, for instance adversarial attacks have unsettled early adopters and are threatening to hinder wider scale adoption of this technology. The problem for real-world applicability lies in being able to assess the risk of applying these technologies. In this discussion-paper we describe the process of arriving at a machine-learnt neural network classifier pointing out safety and security vulnerabilities in that workflow, citing relevant research where appropriate.
URI: https://digitalcollection.zhaw.ch/handle/11475/25396
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Embedded Systems (InES)
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Doran_Security-safety-aspects-AI-industry-applications_EmbeddedWorld.pdf710.2 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.