BSSA-BiT: A Big Data-Based IoT Intrusion Detection Model

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 7

Year of Publication : 2025

Authors : S. Ravishankar, P. Kanmani

10.14445/23488549/IJECE-V12I7P134

How to Cite?

S. Ravishankar, P. Kanmani, "BSSA-BiT: A Big Data-Based IoT Intrusion Detection Model," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 7, pp. 428-442, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I7P134

Abstract:

The size of the Internet and network traffic is increasing constantly, with data generated at an extremely fast rate in petabytes. This data can be classified as Big Data (BD) due to its substantial volume, veracity, Velocity, and variety. The proliferation of usage is accompanied by an increase in security risks to networks like the Internet of Things (IoT). Identifying intrusions in a BD context is challenging. Numerous Intrusion-Detection Systems (IDSs) have been developed for various network attacks; however, most of these IDSs are either incapable of identifying unknown attacks or cannot respond. Deep Learning (DL) algorithms, recently utilized for extensive BD analysis, have demonstrated exceptional performance and efficiency in detecting intrusions. Hence, this research proposes a BD-based IoT intrusion detection model using the DL algorithm with Apache Spark for attack detection and classification. The developed research model incorporates the Binary Salp Swarm Algorithm (BSSA) technique for feature selection and the Bidirectional Transformer (BiT) method for attack detection and classification. For training and evaluation, the CIC-IoT-23 BD dataset is collected and used. Using Apache Spark, the data is preprocessed with multiple preprocessing phases such as data cleaning, normalization, oversampling, and encoding. The BSSA technique selects the most optimal features that help the BiT classifier for accurate attack detection, minimizing dimensionality and enhancing learning efficiency. The BSSA-BiT model attained 98.85% accuracy, 98.59% detection rate, 98.94% precision, and 98.70% F1-score in multiclass classification, and compared to other models, it outperformed and demonstrated as an effective IDS model.

Keywords:

Big Data, Intrusion detection, IoT, Deep Learning, BSSA, BiT, Apache spark.

References:

[1] Afzal Badshah et al., “Big Data Application: Overviews, Challenge and Future,” Artificial Intelligence Reviews, vol. 57, pp. 1-49, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Faheem Ullah, and Muhammad Ali Babar, “Architectural Tactic for Big Data Cybersecurity Analytic System: A Review,” Journal of System and Software, vol. 151, pp. 81-118, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Srikanth Thudumu et al., “A Comprehensive Survey of Anomaly Detection Techniques for High Dimensional Big Data,” Journal of Big Data, vol. 7, pp. 1-30, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mohammad Shahnawaz, and Manish Kumar, “A Comprehensive Survey on Big Data Analytic: Characteristics, Tool and Technique,” ACM Computing Surveys, vol. 57, no. 8, pp. 1-33, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Isaac Kofi Nti et al., “A Mini-Reviews of Machine Learning in Big Data Analytic: Application, Challenge, and Prospect,” Big Data Mining and Analytics, vol. 5, no. 2, pp. 81-97, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Lidong Wang, and Randy Jones, “Big Data Analytics in Cyber Security: Network Traffic and Attacks,” Journal of Computers Information System, vol. 61, no. 5, pp. 410-417, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Nour Moustafa, A Systemic IoT-Fog-Cloud Architecture for Big-Data Analytics and Cyber Security Systems: A Review of Fog Computing, 1st ed., Secure Edge Computing, CRC Press, pp. 1-10, 2021.
[Google Scholar] [Publisher Link]
[8] Zahedi Azam, Motaharul Islam, and Mohammad Nurul Huda, “Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis through Decision Tree,” IEEE Access, vol. 11, pp. 80348-80391, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Seshagirirao Lekkala, Raghavaiah Avula, and Priyanka Gurijala, “Big Data and AI/ML in Threats Detections: A New Era of Cybersecurity,” Journal of Artificial Intelligences and Big Data, vol. 2, no. 1, pp. 32-48, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Duan Dai, and Sahar Boroomand, “A Review of Artificial Intelligence to Enhance the Security of Big Data Systems: State-of-Art, Methodologies, Applications, and Challenges,” Archives of Computational Method in Engineering, vol. 29, no. 2, pp. 1291-1309, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] V. Suresh Kumar, “A Big Data Analytical Framework for Intrusion Detection Based On Novel Elephant Herding Optimized Finite Dirichlet Mixture Models,” International Journal of Data Informatics and Intelligent Computing, vol. 2, no. 2, pp. 11-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Noha Hussen et al., “A Full Streaming Big Data Framework for Cybersecurity Based on Optimized Deep Learning Algorithms,” IEEE Access, vol. 11, pp. 65675-65688, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mohammad Mehedi Hassan et al., “A Hybrid Deep Learning Model for Efficient Intrusions Detections in Big Data Environments,” Information Science, vol. 513, pp. 386-396, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Hong Wang, “A Network Intrusion Security Detection Method Using BiLSTM-CNN in Big Data Environment,” Journal of Information Processing System, vol. 19, no. 5, pp. 688-701, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Soosan Naderi Mighan, and Mohsen Kahani, “A Novel Scalable Intrusions Detections System based on Deep Learning,” International Journals of Information Security, vol. 20, no. 3, pp. 387-403, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mohamed Abushwereb et al., “An Accurate IoT Intrusions Detections Framework using Apache Sparks,” arXiv preprint, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Selvam Saravanan, and Uma Maheswari Balasubramanian, “An Adaptive Scalable Data Pipelines for Multiclass Attacks Classifications in Large-Scale IOT Network,” Big Data Mining and Analytics, vol. 7, no. 2, pp. 500-511, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Abdallah A. Alhabshy, Bashar I. Hameed, and Kamal Abdelraouf Eldahshan, “An Ameliorated Multiattack Network Anomaly Detection in Distributed Big Data System-Based Enhanced Stacking Multiple Binary Classifiers,” IEEE Access, vol. 10, pp. 52724-52743, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Riyaz Ahamed Ariyaluran Habeeb et al., “Clustering-Based Real-Time Anomaly Detection—A Breakthrough in Big Data Technologies,” Transaction on Emerging Telecommunication Technologies, vol. 33, no. 8, pp. 1-27, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Rong Chen, “Design and Protection Strategy of Distributed Intrusions Detections Systems in Big Data Environments,” Computational Intelligences and Neurosciences, vol. 2022, no. 1, pp. 1-7, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Guo Yunhong, and Tang Guoping, “Intelligent Analysis and Dynamic Security of Networks Traffics in Contexts of Big Data,” Journal of Cyber Security and Mobility, vol. 13, no. 5, pp. 823-842, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Yixuan Wu et al., “Intelligent Intrusion Detection for Internet of Things Security: A Deep Convolutional Generative Adversarial Network-Enabled Approach,” IEEE Internet of Things Journals, vol. 10, no. 4, pp. 3094-3106, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Farah Jemili, Rahma Meddeb, and Ouajdi Korbaa, “Intrusions Detections Based on Ensembled Learning for Big Data Classifications,” Cluster Computing, vol. 27, pp. 3771-3798, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Bhukya Madhu et al., “Intrusion Detection Models for IOT Networks via Deep Learning Approaches,” Measurement: Sensors, vol. 25, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Murat Dener, Gökçe Ok, and Abdullah Orman, “Malwares Detections using Memory Analysis Data in Big Data Environments,” Applied Sciences, vol. 12, no. 17, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Feilu Hang et al., “Research on the Application of Network Security Defence in Database Security Services based on Deep Learning Integrated with Big Data Analytics,” International Journal of Intelligent Network, vol. 5, pp. 101-109, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Viet Anh Phan, Jan Jerabek, and Lukas Malina, “Comparison of Multiple Feature Selection Techniques for Machine Learning-Based Detection of IoT Attacks,” Proceedings of the 19th International Conference on Availability, Reliability and Security, Vienna Austria, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Seyed Mohammad Hadi Mirsadeghi et al., “Learning From Few Cyber-Attacks: Addressing the Class Imbalance Problem in Machine Learning-Based Intrusion Detection in Software-Defined Networking,” IEEE Access, vol. 11, pp. 140428-140442, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Dasheng Chen et al., “Identification of Network Traffic Intrusion Using Decision Tree,” Journal of Sensors, vol. 2023, no. 1, pp. 1-9, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] S. Jayachitra et al., “An Efficient Ranking Based Binary Salp Swarm Optimization for Feature Selection in High Dimensional Datasets,” Measurement: Sensors, vol. 35, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Sayar Singh Shekhawat et al., “bSSA: Binary Salp Swarm Algorithm with Hybrid Data Transformation for Feature Selection,” IEEE Access, vol. 9, pp. 14867-14882, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Murat Tezgider, Beytullah Yildiz, and Galip Aydin, “Text Classification using Improved Bidirectional Transformer,” Concurrency and Computations: Practice and Experience, vol. 34, no. 9, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Hany El-Ghaish, and Emadeldeen Eldele, “ECGTransForm: Empowering Adaptive ECG Arrhythmias Classifications Frameworks with Bidirectional Transformers,” Biomedical Signals Processing and Control, vol. 89, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]