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 | Size | Format | |
|---|---|---|---|---|
| 2022_Doran_Security-safety-aspects-AI-industry-applications_EmbeddedWorld.pdf | 710.2 kB | Adobe PDF |  View/Open |
Show full item record
Doran, H. D. (2022). Security and safety aspects of AI in industry applications [Conference paper]. In A. Sikora (Ed.), Proceedings of Embedded World Conference 2022 (pp. 373–378). WEKA. https://doi.org/10.48550/arXiv.2207.10809
Doran, H.D. (2022) ‘Security and safety aspects of AI in industry applications’, in A. Sikora (ed.) Proceedings of Embedded World Conference 2022. WEKA, pp. 373–378. Available at: https://doi.org/10.48550/arXiv.2207.10809.
H. D. Doran, “Security and safety aspects of AI in industry applications,” in Proceedings of Embedded World Conference 2022, Jun. 2022, pp. 373–378. doi: 10.48550/arXiv.2207.10809.
DORAN, Hans Dermot, 2022. Security and safety aspects of AI in industry applications. In: Axel SIKORA (Hrsg.), Proceedings of Embedded World Conference 2022. Conference paper. WEKA. 23 Juni 2022. S. 373–378. ISBN 978-3-645-50194-1
Doran, Hans Dermot. 2022. “Security and Safety Aspects of AI in Industry Applications.” Conference paper. In Proceedings of Embedded World Conference 2022, edited by Axel Sikora, 373–78. WEKA. https://doi.org/10.48550/arXiv.2207.10809.
Doran, Hans Dermot. “Security and Safety Aspects of AI in Industry Applications.” Proceedings of Embedded World Conference 2022, edited by Axel Sikora, WEKA, 2022, pp. 373–78, https://doi.org/10.48550/arXiv.2207.10809.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.