Gärtner, S.; Oberle, M.: Local Differential Privacy In Smart Manufacturing: Application Scenario, Mechanisms and Tools. In: Herberger, D.; Hübner, M. (Eds.): Proceedings of the Conference on Production Systems and Logistics: CPSL 2022. Hannover : publish-Ing., 2022, S. 482-491. DOI: https://doi.org/10.15488/12125
Abstract: | |
To utilize the potential of machine learning and deep learning, enormous amounts of data are required. To find the optimal solution, it is beneficial to share and publish data sets. Due to privacy leaks in publically released datasets and the exposure of sensitive information of individuals by attackers, the research field of differential privacy addresses solutions to avoid this in the future. Compared to other domains, the application of differential privacy in the manufacturing context is very challenging. Manufacturing data contains sensitive information about the companies and their process knowledge, products, and orders. Furthermore, data of individuals operating machines could be exposed and thus their performance evaluated. This paper describes scenarios of how differential privacy can be used in the manufacturing context. In particular, the potential threats that arise when sharing manufacturing data are addressed. This is described by identifying different manufacturing parameters and their variable types. Simplified examples show how the differentially private mechanisms can be applied to binary, numeric, categorical variables, and time series. Finally, libraries are presented which enable the productive use of differential privacy. | |
License of this version: | CC BY 3.0 DE |
Document Type: | BookPart |
Publishing status: | publishedVersion |
Issue Date: | 2022 |
Appears in Collections: | Proceedings CPSL 2022 Proceedings CPSL 2022 |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | United States | 50 | 21.83% | |
2 | Germany | 49 | 21.40% | |
3 | China | 22 | 9.61% | |
4 | India | 11 | 4.80% | |
5 | No geo information available | 8 | 3.49% | |
6 | United Kingdom | 8 | 3.49% | |
7 | Japan | 7 | 3.06% | |
8 | Hong Kong | 6 | 2.62% | |
9 | Korea, Republic of | 5 | 2.18% | |
10 | Iran, Islamic Republic of | 5 | 2.18% | |
other countries | 58 | 25.33% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.