A4 Artikkeli konferenssijulkaisussa
Anonymization as homeomorphic data space transformation for privacy-preserving deep learning (2021)


Girka, A., Terziyan, V., Gavriushenko, M., & Gontarenko, A. (2021). Anonymization as homeomorphic data space transformation for privacy-preserving deep learning. In F. Longo, M. Affenzeller, & A. Padovano (Eds.), ISM 2020 : Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing (180, pp. 867-876). Elsevier. Procedia Computer Science. https://doi.org/10.1016/j.procs.2021.01.337


JYU-tekijät tai -toimittajat


Julkaisun tiedot

Julkaisun kaikki tekijät tai toimittajat: Girka, Anastasiia; Terziyan, Vagan; Gavriushenko, Mariia; Gontarenko, Andrii

Emojulkaisu: ISM 2020 : Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing

Emojulkaisun toimittajat: Longo, Francesco; Affenzeller, Michael; Padovano, Antonio

Konferenssi:

  • International Conference on Industry 4.0 and Smart Manufacturing

Konferenssin paikka ja aika: Virtual Online Conference, 23.-25.11.2020

Lehti tai sarja: Procedia Computer Science

eISSN: 1877-0509

Julkaisuvuosi: 2021

Volyymi: 180

Artikkelin sivunumerot: 867-876

Kirjan kokonaissivumäärä: 1058

Kustantaja: Elsevier

Julkaisumaa: Alankomaat

Julkaisun kieli: englanti

DOI: https://doi.org/10.1016/j.procs.2021.01.337

Julkaisun avoin saatavuus: Avoimesti saatavilla

Julkaisukanavan avoin saatavuus: Kokonaan avoin julkaisukanava

Julkaisu on rinnakkaistallennettu (JYX): https://jyx.jyu.fi/handle/123456789/74351


Tiivistelmä

Industry 4.0 is largely data-driven nowadays. Owners of the data, on the one hand, want to get added value from the data by using remote artificial intelligence tools as services, on the other hand, they concern on privacy of their data within external premises. Ideal solution for this challenge would be such anonymization of the data, which makes the data safe in remote servers and, at the same time, leaves the opportunity for the machine learning algorithms to capture useful patterns from the data. In this paper, we take the problem of supervised machine learning with deep feedforward neural nets and provide an anonymization algorithm (based on the homeomorphic data space transformation), which guarantees privacy of the data and allows neural networks to learn successfully. We made several experiments to show how much the performance of the trained neural nets will suffer from the deepening of the anonymization power.
See presentation slides: https://ai.it.jyu.fi/ISM-2020-Anonymization.pptx


YSO-asiasanat: esineiden internet; tiedonlouhinta; yksityisyys; koneoppiminen; neuroverkot; topologia

Vapaat asiasanat: industry 4.0; privacy; neural network; deep learning; topology


Liittyvät organisaatiot


OKM-raportointi: Kyllä

Raportointivuosi: 2021

JUFO-taso: 1


Viimeisin päivitys 2024-03-04 klo 20:06