A Deep Learning-Based Security Model for ERP-Integrated IoT in National Defense Manufacturing Environments
DOI:
https://doi.org/10.63282/Keywords:
Deep Learning, IoT Security, National Defense, Smart Manufacturing, Cybersecurity, Anomaly Detection, CNN, LSTMAbstract
The rise of Industry 4.0 has brought us to a new era of smart manufacturing environments, and interoperability between Enterprise Resource Planning (ERP) systems and the Internet of Things (IoT) is at the centre stage. Such transformation is especially important in a national defense manufacturing settings that require data integrity, secrecy, and responsiveness in real-time. The current cybersecurity controls can no longer withstand the more advanced forms of attack. In this article, a new deep learning-based security framework is proposed for ERP-integrated IoT infrastructures in national defence manufacturing. The given model utilises Deep Neural Networks (DNNs), Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs) to identify aberrations and predict potential breaks. Our model, unlike the traditional static systems implemented based on the use of rule-based systems, learns and evolves with the system, and makes it possible to mitigate the threat proactively. We describe the architecture design, comprising several layers: a data acquisition layer, a pre-processing layer, a feature extraction module, an anomaly detection core, and a feedback system that upgrades the learning model. Its heterogeneous combination of LSTM and CNN improves detection rates and reduces false positives, and thus deals with issues in time-sequenced and structured ERP-IoT data. Our approach incorporates simulation of datasets based on real-time ERP-IoT communication in the case of defense, with labeled datasets enhanced with vectors related to cyber-attacks. Experimental studies indicate that our model has a detection rate of 98.7% and simultaneously mitigates false positives by 30% compared to other models. We present the demonstration of the actual use in a production facility of a real defense company and present the insights on the scale and possibilities to integrate it into traditional ERP-IoT stacks. The conclusion of the research provides future directions that entail federated learning and quantum-resilient security layers to protect national defense cyber-physical systems more
Downloads
References
[1] Lee, I., & Lee, K. (2015). The Internet of Things (IoT): Applications, investments, and challenges for enterprises. Business horizons, 58(4), 431-440.
[2] Kim, G., Lee, S., & Kim, S. (2014). A novel hybrid intrusion detection method integrating anomaly detection with misuse detection. Expert Systems with Applications, 41(4), 1690-1700.
[3] Vinayakumar, R., Alazab, M., Soman, K. P., Poornachandran, P., Al-Nemrat, A., & Venkatraman, S. (2019). Deep Learning Approach for Intelligent Intrusion Detection Systems. IEEE Access, 7, 41525-41550.
[4] Abeshu, A., & Chilamkurti, N. (2018). Deep learning: The frontier for distributed attack detection in fog-to-things computing. IEEE Communications Magazine, 56(2), 169-175.
[5] Garcia-Teodoro, P., Diaz-Verdejo, J., Maciá-Fernández, G., & Vázquez, E. (2009). Anomaly-Based Network Intrusion Detection: Techniques, Systems, and Challenges. computers & security, 28(1-2), 18-28.
[6] Zuech, R., Khoshgoftaar, T. M., & Wald, R. (2015). Intrusion detection and big heterogeneous data: a survey. Journal of Big Data, 2(1), 3.
[7] Zarpelão, B. B., Miani, R. S., Kawakani, C. T., & De Alvarenga, S. C. (2017). A survey of intrusion detection in the Internet of Things. Journal of Network and Computer Applications, 84, 25-37.
[8] Sun, M., Konstantelos, I., & Strbac, G. (2018). A deep learning-based feature extraction framework for system security assessment. IEEE Transactions on Smart Grid, 10(5), 5007-5020.
[9] Sarker, I. H., Abushark, Y. B., Alsolami, F., & Khan, A. I. (2020). Intrudtree: a machine learning based cybersecurity intrusion detection model. Symmetry, 12(5), 754.
[10] Devi, K., Paulraj, D., & Muthusenthil, B. (2020). Deep learning based security model for cloud-based task scheduling. KSII Transactions on Internet and Information Systems (TIIS), 14(9), 3663-3679.
[11] Kaur, P., Sharma, M., & Mittal, M. (2018). A big data and machine learning-based secure healthcare framework. Procedia computer science, 132, 1049-1059.
[12] Kumar, N. (2022). IoT-Enabled Real-Time Data Integration in ERP Systems. International Journal of Scientific Research in Science, Engineering and Technology.
[13] Alsamhi, S. H., Shvetsov, A. V., Kumar, S., et al. (2022). Deep learning for cybersecurity in Industrial Internet of Things: Approaches, challenges, and future directions. IEEE Access, 10, 85792–85812.
[14] Sarker, I. H. (2021). Deep cybersecurity: a comprehensive overview from a neural network and deep learning perspective. SN Computer Science, 2(3), 154.
[15] Hassan, M. M., Gumaei, A., Aloqaily, M., & Fortino, G. (2019). A deep learning approach for energy-efficient resource management in IoT systems. Future Generation Computer Systems, 104, 38–51.
[16] Odell, L. A., Farrar-Foley, B. T., Kinkel, J. R., Moorthy, R. S., & Schultz, J. A. (2012). Beyond Enterprise Resource Planning (ERP): The Next Generation Enterprise Resource Planning Environment (No. IDAHQP4852).
[17] Hill, C. W. (2007). Transforming the force: a comparative analysis of the Department of Defense's (DoD's) Enterprise Resource Planning (ERP) systems.
[18] Vassilev, V., Donchev, D., & Tonchev, D. (2021). Impact of false positives and false negatives on security risks in transactions under threat.
[19] Bian, J., Al Arafat, A., Xiong, H., Li, J., Li, L., Chen, H., ... & Guo, Z. (2022). Machine learning in real-time Internet of Things (IoT) systems: A survey. IEEE Internet of Things Journal, 9(11), 8364-8386.
[20] Yue, Y., Li, S., Legg, P., & Li, F. (2021). Deep Learning‐Based Security Behaviour Analysis in IoT Environments: A Survey. Security and communication Networks, 2021(1), 8873195.
[21] Awajan, A. (2023). A novel deep learning-based intrusion detection system for IOT networks. Computers, 12(2), 34.
[22] Thirunagalingam, A. (2023). Improving Automated Data Annotation with Self-Supervised Learning: A Pathway to Robust AI Models Vol. 7, No. 7,(2023) ITAI. International Transactions in Artificial Intelligence, 7(7).
