Designing a hybrid algorithm that combines deep learning and PSO for proactive detection of attacks in IoT networks
Subject Areas : Machine learning
Zahra Bakhshali
1
,
Alireza Poorebrahimi
2
*
,
Ahmad Ebrahimi
3
,
Nazanin Pilevari
4
1 - Department of Information Technology Management, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - Corresponding Author,Department of Industrial Management,Karaj Branch,Islamic Azad University,Alborz,Iran.
3 - Department of Industrial and Technology Management, Science and Research Branch, Islamic Azad University, Tehran, Iran
4 - Department of Industrial Management,West Tehran Branch,Islamic Azad University,Tehran,Iran.
Keywords: Deep Learning Algorithms, Internet of Things, IoT attacks, PSO algorithm,
Abstract :
With the rapid development of Internet of Things (IoT) technology and the boom in associated information volumes, the need for robust and green security systems for detecting cyber-assaults has been mentioned. Accurate identification of cyber-attacks in this area is hard because of the complexity and variety of records. Extensive studies have been conducted to decorate the accuracy and performance of attack detection structures, yet there remains large room for improvement.
This offers a unique method for optimizing assault detection in IoT. The research seeks to seriously decorate the accuracy and efficiency of attack detection fashions by using a mixture of deep mastering algorithms (CNN-GRU-LSTM) and hyperparameter optimization through the Particle Swarm Optimization (PSO) set of rules.
Initially, data is loaded and pre-processed from a CSV report. After disposing of unnecessary capabilities and sampling the statistics, magnificence weights are calculated to address information imbalance. Subsequently, a hybrid CNN-GRU-LSTM model is defined and skilled. Next, the PSO set of rules is applied to optimize the model's hyperparameters, choosing the high-quality combination of functions and parameters to decorate the accuracy and efficiency of attack detection.
The sizable improvement in the accuracy and efficiency of assault detection demonstrates that the use of the hybrid CNN-GRU-LSTM set of rules combined with hyperparameter optimization through PSO can contribute to the improvement of greater advanced and efficient security systems inside the IoT area. These findings pave the way for future studies in optimizing attack detection fashions using numerous devices getting to know algorithms.
[1] M. Haras and T. Skotnicki, “Thermoelectricity for IoT – A review,” 2018. doi: 10.1016/j.nanoen.2018.10.013.
[2] M. Nazarpour, N. Nezafati, and S. Shokouhyar, “Detection of Attacks and Anomalies in the Internet of Things System using Neural Networks Based on Training with PSO Algorithms, Fuzzy PSO, Comparative PSO and Mutative PSO,” Journal of Information Systems and Telecommunication, vol. 10, no. 40, 2022, doi: 10.52547/jist.16307.10.40.270.
[3] M. Sedighmanesh, H. ZandHessami, M. Alborzi, and M. Khayyatian, “Reducing Energy Consumption in Sensor-Based Internet of Things Networks Based on Multi-Objective Optimization Algorithms,” Journal of Information Systems and Telecommunication, vol. 10, no. 39, 2022, doi: 10.52547/jist.15639.10.39.180.
[4] K. M. sedighimanesh mohammad, Zandhessami Hessam, Alborzi Mahmood, “Energy Efficient Routing-Based Clustering Protocol Using Computational Intelligence Algorithms in Sensor-Based IoT,” Journal of Information Systems and Telecommunication (JIST), vol. 33, no. 9, 2021, doi: 10.52547/jist.9.33.55.
[5] A. Ullah, N. Javaid, O. Samuel, M. Imran, and M. Shoaib, “CNN and GRU based Deep Neural Network for Electricity Theft Detection to Secure Smart Grid,” in 2020 International Wireless Communications and Mobile Computing, IWCMC 2020, 2020. doi: 10.1109/IWCMC48107.2020.9148314.
[6] A. M. Banaamah and I. Ahmad, “Intrusion Detection in IoT Using Deep Learning,” Sensors, vol. 22, no. 21, 2022, doi: 10.3390/s22218417.
[7] C. U. Om Kumar, S. Marappan, B. Murugeshan, and P. M. R. Beaulah, “Intrusion Detection Model for IoT Using Recurrent Kernel Convolutional Neural Network,” Wirel Pers Commun, vol. 129, no. 2, 2023, doi: 10.1007/s11277-022-10155-9.
[8] M. A. Khan, “HCRNNIDS: Hybrid convolutional recurrent neural network-based network intrusion detection system,” Processes, vol. 9, no. 5, 2021, doi: 10.3390/pr9050834.
[9] A. Dushimimana, T. Tao, R. Kindong, and A. Nishyirimbere, “Bi-directional Recurrent Neural network for Intrusion Detection System (IDS) in the internet of things (IoT),” International Journal of Advanced Engineering Research and Science, vol. 7, no. 3, 2020, doi: 10.22161/ijaers.73.68.
[10] N. W. Khan et al., “A hybrid deep learning-based intrusion detection system for IoT networks,” Mathematical Biosciences and Engineering, vol. 20, no. 8, 2023, doi: 10.3934/mbe.2023602.
[11] S. A. Alabady, F. Al-Turjman, and S. Din, “A Novel Security Model for Cooperative Virtual Networks in the IoT Era,” Int J Parallel Program, vol. 48, no. 2, 2020, doi: 10.1007/s10766-018-0580-z.
[12] A. A. Alahmadi et al., “DDoS Attack Detection in IoT-Based Networks Using Machine Learning Models: A Survey and Research Directions,” 2023. doi: 10.3390/electronics12143103.
[13] L. Xiao, X. Wan, X. Lu, Y. Zhang, and D. Wu, “IoT Security Techniques Based on Machine Learning: How Do IoT Devices Use AI to Enhance Security?,” IEEE Signal Process Mag, vol. 35, no. 5, 2018, doi: 10.1109/MSP.2018.2825478.
[14] M. Jain, V. Saihjpal, N. Singh, and S. B. Singh, “An Overview of Variants and Advancements of PSO Algorithm,” 2022. doi: 10.3390/app12178392.
[15] J. Fang, W. Liu, L. Chen, S. Lauria, A. Miron, and X. Liu, “A Survey of Algorithms, Applications and Trends for Particle Swarm Optimization,” International Journal of Network Dynamics and Intelligence, 2023, doi: 10.53941/ijndi0201002.
[16] A. Aribisala, M. S. Khan, and G. Husari, “Feed-Forward Intrusion Detection and Classification on a Smart Grid Network,” in 2022 IEEE 12th Annual Computing and Communication Workshop and Conference, CCWC 2022, 2022. doi: 10.1109/CCWC54503.2022.9720898.
[17] W. H. Lin, P. Wang, B. H. Wu, M. S. Jhou, K. M. Chao, and C. C. Lo, “Behaviorial-Based Network Flow Analyses for Anomaly Detection in Sequential Data Using Temporal Convolutional Networks,” in Lecture Notes on Data Engineering and Communications Technologies, vol. 41, 2020. doi: 10.1007/978-3-030-34986-8_12.
[18] M. Chattopadhyay, “Modelling of intrusion detection system using artificial intelligence—evaluation of performance measures,” Studies in Fuzziness and Soft Computing, vol. 319, 2015, doi: 10.1007/978-3-319-12883-2_11.