A4 Article in conference proceedings
Encryption and Generation of Images for Privacy-Preserving Machine Learning in Smart Manufacturing (2023)


Terziyan, V., Malyk, D., Golovianko, M., & Branytskyi, V. (2023). Encryption and Generation of Images for Privacy-Preserving Machine Learning in Smart Manufacturing. In F. Longo, M. Affenzeller, A. Padovano, & S. Weiming (Eds.), 4th International Conference on Industry 4.0 and Smart Manufacturing (217, pp. 91-101). Elsevier. Procedia Computer Science. https://doi.org/10.1016/j.procs.2022.12.205


JYU authors or editors


Publication details

All authors or editors: Terziyan, Vagan; Malyk, Diana; Golovianko, Mariia; Branytskyi, Vladyslav

Parent publication: 4th International Conference on Industry 4.0 and Smart Manufacturing

Parent publication editors: Longo, Francesco; Affenzeller, Michael; Padovano, Antonio; Weiming, Shen

Conference:

  • International Conference on Industry 4.0 and Smart Manufacturing

Place and date of conference: Linz, Austria, 2.-4.11.2022

Journal or series: Procedia Computer Science

eISSN: 1877-0509

Publication year: 2023

Volume: 217

Pages range: 91-101

Number of pages in the book: 1954

Publisher: Elsevier

Publication country: Netherlands

Publication language: English

DOI: https://doi.org/10.1016/j.procs.2022.12.205

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/85094


Abstract

Current advances in machine (deep) learning and the exponential growth of data collected by and shared between smart manufacturing processes give a unique opportunity to get extra value from that data. The use of public machine learning services actualizes the issue of data privacy. Ordinary encryption protects the data but could make it useless for the machine learning objectives. Therefore, “privacy of data vs. value from data” is the major dilemma within the privacy preserving machine learning activity. Special encryption techniques or synthetic data generation are being in focus to address the issue. In this paper, we discuss a complex hybrid protection algorithm, which assumes sequential use of two components: homeomorphic data space transformation and synthetic data generation. Special attention is given to the privacy of image data. Specifics of image representation require special approaches towards encryption and synthetic image generation. We suggest use of (convolutional, variational) autoencoders and pre-trained feature extractors to enable applying privacy protection algorithms on top of the latent feature vectors captured from the images, and we updated the hybrid algorithms composed of homeomorphic transformation-as-encryption plus synthetic image generation accordingly. We show that an encrypted image can be reconstructed (by the pre-trained Decoder component of the convolutional variational autoencoder) into a secured representation from the extracted (by either the Encoder or a feature extractor) and encrypted (homeomorphic transformation of the latent space) feature vector.
See presentation slides: https://ai.it.jyu.fi/ISM-2022-Image_Encryption.pptx


Keywords: industry; manufacturing engineering; machine learning; computer vision; data protection; anonymity; encryption

Free keywords: Industry 4.0; data privacy; anonymization; syntetic data generation; image processing; autoencoders


Contributing organizations


Ministry reporting: Yes

Reporting Year: 2023

JUFO rating: 1


Last updated on 2024-03-07 at 00:05