Title: Digital clones and digital immunity: adversarial training handles both

Authors: Vladyslav Branytskyi; Mariia Golovianko; Svitlana Gryshko; Diana Malyk; Vagan Terziyan; Tuure Tuunanen

Addresses: Department of Artificial Intelligence, NURE – Kharkiv National University of Radio Electronics, Nauky Avenue 14, Kharkiv, 61166, Ukraine ' Department of Artificial Intelligence, NURE – Kharkiv National University of Radio Electronics, Nauky Avenue 14, Kharkiv, 61166, Ukraine ' Department of Economic Cybernetics, Kharkiv National University of Radio Electronics, Nauky Avenue 14, Kharkiv, 61166, Ukraine ' Department of Artificial Intelligence, NURE – Kharkiv National University of Radio Electronics, Nauky Avenue 14, Kharkiv, 61166, Ukraine ' Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40100, Finland ' Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40100, Finland

Abstract: Smart manufacturing needs digital clones of physical objects (digital twins) and human decision-makers (cognitive clones). The latter requires use of machine learning to capture hidden personalised decision models from humans. Machine learning nowadays is a subject of various adversarial attacks (poisoning, evasion, etc.). Responsible use of machine learning requires digital immunity (the capability of smart systems to operate robustly in adversarial conditions). Both problems (clones and immunity training) have the same backbone solution, which is adversarial training (learning on automatically generated adversarial samples). In this study, we design and experimentally test special algorithms for adversarial samples generation to fit simultaneously both purposes: to better personalise decision models for digital clones and to train digital immunity, thus, ensuring robustness of autonomous decision models. We demonstrate that our algorithms facilitate the desired robustness and accuracy of the training process.

Keywords: digital cloning; digital immunity; Industry 4.0; adversarial machine learning; adversarial example generation; machine learning; generative adversarial networks; process modelling.

DOI: 10.1504/IJSPM.2022.126106

International Journal of Simulation and Process Modelling, 2022 Vol.18 No.2, pp.124 - 139

Received: 01 Feb 2021
Accepted: 16 Oct 2021
Published online: 11 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article