Cyber-physical system security for manufacturing industry 4.0 using LSTM-CNN parallel orchestration

Interoperability among different machines, systems, and humans connected via the Internet of Things (IoT) has blessed Industry 4.0 with numerous advantages over the years. However, these benefits have unleashed risks of cyber attacks on internet-connected manufacturing units such as autonomous intelligent computer-controlled cutting (ICNC) machines. These are used in different manufacturing industries to ensure high precision and faster production. Over the Internet these machines receive product designs and instructions of how to produce them. Intrusions through malicious code embedded in the design can hamper precision and cause production delays, resulting in significant revenue loss. This paper presents an innovative cyber-physical system (CPS) security mechanism, using a long short-term memory (LSTM) network and a convolutional neural network (CNN) coordinated by a parallel orchestration (PLO) algorithm. It detects intrusions from both image and text data with 90.85% and 91.66% accuracy, respectively. Applying the proposed methodology in a simulated manufacturing industry shows an average yearly successful intrusion reduction from 184 to 15, saving an average of $30,474 in revenue. Its innovative concept, the distinctive mechanism of the PLO algorithm, and applying it in a simulated manufacturing industry make the proposed security system superior to comparable approaches.

[1] S. Munirathinam, ‘‘Industry 4.0: Industrial Internet of Things (IIOT),’’ in Advances in Computers, vol. 117. Amsterdam, The Netherlands: Elsevier, 2020, pp. 129–164.
[2] M. Kerin and D. T. Pham, ‘‘A review of emerging Industry 4.0 technologies in remanufacturing,’’ J. Cleaner Prod., vol. 237, Nov. 2019, Art. no. 117805.
[3] H. Ravichandran, Intelligent Safety: How to Protect Your Connected Family From Big Cybercrime. New York, NY, USA: Simon and Schuster, 2023.
[4] H. Kayan, M. Nunes, O. Rana, P. Burnap, and C. Perera, ‘‘Cybersecurity of industrial cyber-physical systems: A review,’’ ACM Comput. Surv., vol. 54, no. 11s, pp. 1–35, Jan. 2022.
[5] M. F. Franco, F. Künzler, J. von der Assen, C. Feng, and B. Stiller, ‘‘RCVaR: An economic approach to estimate cyberattacks costs using data from industry reports,’’ Comput. Secur., vol. 139, Apr. 2024, Art. no. 103737.
[6] Z. Humienny, ‘‘New ISO geometrical product specification standards as a response to Industry 4.0 needs,’’ in Proc. 5th Int. Conf. Ind. 4.0 Model Adv. Manuf., Acad. Manage. Perspect. Cham, Switzerland: Springer, Jan. 2020, pp. 306–312.
[7] S. M. Zahraee, S. R. Golroudbary, A. Hashemi, J. Afshar, and M. Haghighi, ‘‘Simulation of manufacturing production line based on arena,’’ Adv. Mater. Res., vol. 933, pp. 744–748, May 2014.
[8] E. C. P. Neto, S. Dadkhah, R. Ferreira, A. Zohourian, R. Lu, and A. A. Ghorbani, ‘‘CICIoT2023: A real-time dataset and benchmark for large-scale attacks in IoT environment,’’ Sensors, vol. 23, no. 13, p. 5941, Jun. 2023.
[9] K. A. Asmitha, V. Puthuvath, K. A. R. Rehiman, and S. L. Ananth, ‘‘Deep learning vs. Adversarial noise: A battle in malware image analysis,’’ Cluster Comput., vol. 27, no. 7, pp. 9191–9220, Oct. 2024.
[10] D. G. S. Pivoto, L. F. F. de Almeida, R. da Rosa Righi,
J. J. P. C. Rodrigues, A. B. Lugli, and A. M. Alberti, ‘‘Cyber-physical systems architectures for industrial Internet of Things applications in Industry 4.0: A literature review,’’ J. Manuf. Syst., vol. 58, pp. 176–192, Jan. 2021.
[11] S. J. Oks, M. Jalowski, M. Lechner, S. Mirschberger, M. Merklein, B. Vogel-Heuser, and K. M. Möslein, ‘‘Cyber-physical systems in the context of Industry 4.0: A review, categorization and outlook,’’ Inf. Syst. Frontiers, vol. 26, no. 5, pp. 1731–1772, Oct. 2024.
[12] G. Lampropoulos and K. Siakas, ‘‘Enhancing and securing cyber-physical systems and Industry 4.0 through digital twins: A critical review,’’ J. Softw., Evol. Process, vol. 35, no. 7, p. 2494, Jul. 2023.
[13] K. Manasa and L. M. I. L. Joseph, ‘‘IoT security vulnerabilities and defensive measures in Industry 4.0,’’ in Advanced Technologies and Societal Change. Cham, Switzerland: Springer, 2023, pp. 71–112.
[14] B. Li, Y. Wu, J. Song, R. Lu, T. Li, and L. Zhao, ‘‘DeepFed: Federated deep learning for intrusion detection in industrial cyber–physical systems,’’ IEEE Trans. Ind. Informat., vol. 17, no. 8, pp. 5615–5624, Aug. 2021.
[15] P. O’Donovan, C. Gallagher, K. Bruton, and D. T. J. O’Sullivan, ‘‘A fog computing industrial cyber-physical system for embedded low-latency machine learning Industry 4.0 applications,’’ Manuf. Lett., vol. 15, pp. 139–142, Jan. 2018.
[16] S. Sharma and K. Guleria, ‘‘Machine learning techniques for intelligent vulnerability detection in cyber-physical systems,’’ in Proc. Int. Conf. Data Analytics Bus. Ind. (ICDABI), Oct. 2022, pp. 200–204.
[17] A. S. Rajawat, S. B. Goyal, P. Bedi, N. B. Constantin, M. S. Raboaca, and C. Verma, ‘‘Cyber-physical system for industrial automation using quantum deep learning,’’ in Proc. 11th Int. Conf. Syst. Model. Advancement Res. Trends (SMART), Dec. 2022, pp. 897–903.
[18] U. Awan, L. Hannola, A. Tandon, R. K. Goyal, and A. Dhir, ‘‘Quantum computing challenges in the software industry. A fuzzy AHP-based approach,’’ Inf. Softw. Technol., vol. 147, Jul. 2022, Art. no. 106896.
[19] M. Abdullahi, H. Alhussian, N. Aziz, S. J. Abdulkadir, and Y. Baashar, ‘‘Deep learning model for cybersecurity attack detection in cyber-physical systems,’’ in Proc. 6th Int. Conf. Comput., Commun., Control Autom. (ICCUBEA, Aug. 2022, pp. 1–5.
[20] R. Alguliyev, Y. Imamverdiyev, and L. Sukhostat, ‘‘Hybrid DeepGCL model for cyber-attacks detection on cyber-physical systems,’’ Neural Comput. Appl., vol. 33, no. 16, pp. 10211–10226, Aug. 2021.
[21] M. Alabadi and A. Habbal, ‘‘Next-generation predictive maintenance: Leveraging blockchain and dynamic deep learning in a domain-independent system,’’ PeerJ Comput. Sci., vol. 9, p. e1712, Dec. 2023.
[22] Y. Wu, H. Cao, G. Yang, T. Lu, and S. Wan, ‘‘Digital twin of intelligent small surface defect detection with cyber-manufacturing systems,’’ ACM Trans. Internet Technol., vol. 23, no. 4, pp. 1–20, Nov. 2023.
[23] I. W. R. Taifa, S. G. Hayes, and I. D. Stalker, ‘‘Computer modelling and simulation of an equitable order distribution in manufacturing through the Industry 4.0 framework,’’ in Proc. Int. Conf. Electr., Commun., Comput.
Eng. (ICECCE), Jun. 2020, pp. 1–6.
[24] A. Dogan and D. Birant, ‘‘Machine learning and data mining in manufacturing,’’ Expert Syst. Appl., vol. 166, Mar. 2021, Art. no. 114060.
[25] S. R. Burri, S. Ahuja, A. Kumar, and A. Baliyan, ‘‘Exploring the effectiveness of optimized convolutional neural network in transfer learning for image classification: A practical approach,’’ in Proc. Int. Conf. Advancement Comput. Comput. Technol. (InCACCT), May 2023, pp. 598–602.
[26] X. Lei, H. Pan, and X. Huang, ‘‘A dilated CNN model for image classification,’’ IEEE Access, vol. 7, pp. 124087–124095, 2019.
[27] P. Gambini, M. Renaud, C. Guillemot, F. Callegati, I. Andonovic, B. Bostica, D. Chiaroni, G. Corazza, S. L. Danielsen, P. Gravey, P. B. Hansen, M. Henry, C. Janz, A. Kloch, R. Krahenbuhl, C. Raffaelli, M. Schilling, A. Talneau, and L. Zucchelli, ‘‘Transparent optical packet switching: Network architecture and demonstrators in the KEOPS project,’’ IEEE J. Sel. Areas Commun., vol. 16, no. 7, pp. 1245–1259, Sep. 1998.
[28] A. Halbouni, T. S. Gunawan, M. H. Habaebi, M. Halbouni, M. Kartiwi, and R. Ahmad, ‘‘CNN-LSTM: Hybrid deep neural network for network intrusion detection system,’’ IEEE Access, vol. 10, pp. 99837–99849, 2022.
[29] S. M. Al-Selwi, M. F. Hassan, S. J. Abdulkadir, and A. Muneer, ‘‘LSTM inefficiency in long-term dependencies regression problems,’’ J. Adv. Res. Appl. Sci. Eng. Technol., vol. 30, no. 3, pp. 16–31, May 2023.
[30] H. Zhao, S. Sun, and B. Jin, ‘‘Sequential fault diagnosis based on LSTM neural network,’’ IEEE Access, vol. 6, pp. 12929–12939, 2018.
[31] Z. Qin, S. Yang, and Y. Zhong, ‘‘Hierarchically gated recurrent neural network for sequence modeling,’’ in Proc. Adv. Neural Inf. Process. Syst., Jan. 2023.
[32] A. Sherstinsky, ‘‘Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network,’’ Phys. D, Nonlinear Phenomena, vol. 404, Mar. 2020, Art. no. 132306.
[33] S. Huda, K. Liu, M. Abdelrazek, A. Ibrahim, S. Alyahya, H. Al-Dossari, and S. Ahmad, ‘‘An ensemble oversampling model for class imbalance problem in software defect prediction,’’ IEEE Access, vol. 6, pp. 24184–24195, 2018.
[34] S. Susan and A. Kumar, ‘‘The balancing trick: Optimized sampling of imbalanced datasets—A brief survey of the recent state of the art,’’ Eng. Rep., vol. 3, no. 4, p. 12298, Apr. 2021.
[35] S. M. Kasongo and Y. Sun, ‘‘A deep learning method with wrapper based feature extraction for wireless intrusion detection system,’’ Comput. Secur., vol. 92, May 2020, Art. no. 101752.
[36] Y. Xu, G. J. Jones, J. Li, B. Wang, and C. Sun, ‘‘A study on mutual information-based feature selection for text categorization,’’ J. Comput. Inf. Syst., vol. 3, no. 3, pp. 1007–1012, 2007.
[37] A. H. Mirza and S. Cosan, ‘‘Computer network intrusion detection using sequential LSTM neural networks autoencoders,’’ in Proc. 26th Signal Process. Commun. Appl. Conf. (SIU), May 2018, pp. 1–4.
[38] L. Dong, D. Fang, X. Wang, W. Wei, R. Damaševičius, R. Scherer, and M. Woźniak, ‘‘Prediction of streamflow based on dynamic sliding window LSTM,’’ Water, vol. 12, no. 11, p. 3032, Oct. 2020.
[39] D. Gibert, C. Mateu, J. Planes, and R. Vicens, ‘‘Using convolutional neural networks for classification of malware represented as images,’’ J. Comput. Virol. Hacking Techn., vol. 15, no. 1, pp. 15–28, Mar. 2019.
[40] L. Nataraj, V. Yegneswaran, P. Porras, and J. Zhang, ‘‘A comparative assessment of malware classification using binary texture analysis and dynamic analysis,’’ in Proc. 4th ACM Workshop Secur. Artif. Intell., Oct. 2011, pp. 21–30.
[41] Z. Zhang and M. R. Sabuncu, ‘‘Generalized cross entropy loss for training deep neural networks with noisy labels,’’ in Proc. Adv. Neural Inf. Process. Syst., vol. 31, Dec. 2018, pp. 8792–8802.
[42] A. Razaque, F. Amsaad, M. J. Khan, S. Hariri, S. Chen, C. Siting, and X. Ji, ‘‘Survey: Cybersecurity vulnerabilities, attacks and solutions in the medical domain,’’ IEEE Access, vol. 7, pp. 168774–168797, 2019.
[43] I. Alsmadi, N. Aljaafari, M. Nazzal, S. Alhamed, A. H. Sawalmeh, C. P. Vizcarra, A. Khreishah, M. Anan, A. Algosaibi, M. A. Al-Naeem, A. Aldalbahi, and A. Al-Humam, ‘‘Adversarial machine learning in text processing: A literature survey,’’ IEEE Access, vol. 10, pp. 17043–17077, 2022.