Adaptive DBSCAN and Federated Learning-Based Anomaly Detection for Resilient Intrusion Detection in Internet of Things Networks

Authors

  • Naresh Kumar Reddy Panga Virtusa Corporation, Engineering Manager, Anthem – VA, USA Author
  • Thanjaivadivel M, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, India Author

Keywords:

Adaptive DBSCAN, Federated Learning, Intrusion Detection System (IDS), Anomaly Detection, Internet of Things (IoT), Security, Machine Learning for Cybersecurity, Real-Time Threat Detection,, Privacy-Preserving AI, Clustering in IoT Networks, Cyber Threat Mitigation

Abstract

The fast growth of the Internet of Things (IoT) has brought with it tremendous security issues, 
necessitating adaptive and privacy-enhancing intrusion detection systems. Conventional 
techniques are not able to cope with changing cyber threats, calling for sophisticated techniques. 
This research suggests a hybrid anomaly detection model that combines Adaptive DBSCAN and 
Federated Learning (FL) to improve accuracy, scalability, and security. Adaptive DBSCAN 
adjusts clustering parameters dynamically, enhancing detection accuracy and noise reduction, 
while FL supports decentralized model training, preserving data privacy. The suggested model 
detects with 95% accuracy, surpassing individual Adaptive DBSCAN (85%) and FL (84%). The 
F1-score increased to 92%, indicating enhanced anomaly classification, with 12% noise reduction 
and 15% enhancement in clustering efficiency. Furthermore, latency was minimized to 250ms, 
and the model is now applicable for real-time usage. The integration of Adaptive DBSCAN and 
FL offers a scalable and robust Intrusion Detection System (IDS) that can efficiently respond to 
dynamic cyber attacks in IoT networks. Experimental results validate that this hybrid solution 
improves detection performance while preserving efficiency and data security. Feature 
enhancement include optimizing the communication overhead to minimize latency further, 
incorporating deep learning methodologies for improved feature extraction, and deploying 
differential privacy mechanisms to enhance security. This work provides a robust, scalable, and 
privacy-preserving anomaly detection framework, with substantial contributions to IoT 
cybersecurity. 

References

Wang, C. Y., Ou, C. L., Zhang, Y. E., Cho, F. M., Chen, P. H., Chang, J. B., & Shieh, C. K. (2018). BotCluster: A session-based P2P botnet clustering system on NetFlow. Computer Networks, 145, 175-189.

Prabhu, C. S. R. (2019). Fog computing, deep learning and big data analytics-research directions (pp. 1-71). Singapore: Springer.

Natarajan, D. R. (2018). A hybrid particle swarm and genetic algorithm approach for optimizing recurrent and radial basis function networks in cloud computing for healthcare disease detection. International Journal of Engineering Research & Science & Technology, 18(1), 198-215.

Parimi, S. S. (2017). Leveraging Deep Learning for Anomaly Detection in SAP Financial Transactions. Available at SSRN 4934907.

Pulakhandam, W., & Vallu, V. R. (2016). Cyber threat detection in federated learning: A secure, AI-powered approach using KNN, GANs, and IOTA. International Journal of Advanced Science, Engineering and Management, 10(4), 1-15.

Lan, K., Wang, D. T., Fong, S., Liu, L. S., Wong, K. K., & Dey, N. (2018). A survey of data mining and deep learning in bioinformatics. Journal of medical systems, 42, 1-20.

Muhammed, T., Mehmood, R., Albeshri, A., & Katib, I. (2018). UbeHealth: A personalized ubiquitous cloud and edge-enabled networked healthcare system for smart cities. IEEE Access, 6, 32258-32285.

Dai, H. N., Wong, R. C. W., Wang, H., Zheng, Z., & Vasilakos, A. V. (2019). Big data analytics for large-scale wireless networks: Challenges and opportunities. ACM Computing Surveys (CSUR), 52(5), 1-36

Natarajan, D. R., Narla, S., & Kethu, S. S. (2019). An intelligent decision-making framework for cloud adoption in healthcare: Combining DOI theory, machine learning, and multi-criteria approaches. International Journal of Engineering Research & Science & Technology, 19(1), 44-60..

Schreyer, M., Sattarov, T., Borth, D., Dengel, A., & Reimer, B. (2017). Detection of anomalies in large scale accounting data using deep autoencoder networks. arXiv preprint arXiv:1709.05254.

Gruhl, C., & Sick, B. (2018). Novelty detection with CANDIES: a holistic technique based on probabilistic models. International Journal of Machine Learning and Cybernetics, 9, 927-945.

Devarajan, M. V. (2019). A comprehensive AI-based detection and differentiation model for neurological disorders using PSP Net and fuzzy logic-enhanced Hilbert-Huang Transform. International Journal of Medical AI and Neurological Research, 7(3), 94-110.

De, S., Zhou, Y., Larizgoitia Abad, I., & Moessner, K. (2017). Cyber–physical–social frameworks for urban big data systems: A survey. Applied Sciences, 7(10), 1017.

Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2017). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE transactions on smart grid, 10(1), 841-851.

Xue, M., Bian, R., Liu, W., & Wang, J. (2018). Defeating untrustworthy testing parties: A novel hybrid clustering ensemble based golden models-free hardware trojan detection method. IEEE Access, 7, 5124-5140.

Wang, X., Sutton, P. C., & Qi, B. (2019). Global mapping of GDP at 1 km2 using VIIRS nighttime satellite imagery. ISPRS International Journal of Geo-Information, 8(12), 580.

Wu, Z., Lu, Z., Zhang, W., Wu, J., Huang, S., & Hung, P. C. (2018). A data-driven approach of performance evaluation for cache server groups in content delivery network. Journal of Parallel and Distributed Computing, 119, 162-171.

Hasan, M., Orgun, M. A., & Schwitter, R. (2018). A survey on real-time event detection from the Twitter data stream. Journal of Information Science, 44(4), 443-463.

Zaidi, S. M. A., Chandola, V., Allen, M. R., Sanyal, J., Stewart, R. N., Bhaduri, B. L., & McManamay, R. A. (2018). Machine learning for energy-water nexus: challenges and opportunities. Big Earth Data, 2(3), 228-267.

Xiao, Y., Jia, Y., Liu, C., Cheng, X., Yu, J., & Lv, W. (2019). Edge computing security: State of the art and challenges. Proceedings of the IEEE, 107(8), 1608-1631.

Erickson, B. J., Korfiatis, P., Akkus, Z., & Kline, T. L. (2017). Machine learning for medical imaging. radiographics, 37(2), 505-515.

Peddi, S., Narla, S., & Valivarthi, D. T. (2018). Advancing geriatric care: Machine learning algorithms and AI applications for predicting dysphagia, delirium, and fall risks in elderly patients. Volume 6, Issue 4.

Kadiyala, B. (2019). Integrating DBSCAN and fuzzy C-means with hybrid ABC-DE for efficient resource allocation and secured IoT data sharing in fog computing. Volume 7, Issue 4.

Peddi, S., Narla, S., & Valivarthi, D. T. (2019). Harnessing artificial intelligence and machine learning algorithms for chronic disease management, fall prevention, and predictive healthcare applications in geriatric care. International Journal of Engineering Research & Science & Technology, 19(1), 1-15.

Jadon, R. (2018). Optimized machine learning pipelines: Leveraging RFE, ELM, and SRC for advanced software development in AI applications. International Journal of Engineering Research & Science Technology, 6(1), 18.

Nippatla, R. P. (2018). A secure cloud-based financial analysis system for enhancing Monte Carlo simulations and Deep Belief Network models using Bulk Synchronous Parallel processing. International Journal of Engineering Research & Science Technology, 6(3), 89.

Gudivaka, B. R. (2019). Big data-driven silicon content prediction in hot metal using Hadoop in blast furnace smelting. International Journal of Information Technology & Computer Engineering, 2347–3657.

Natarajan, D. R., & Kethu, S. S. (2019). Optimized cloud manufacturing frameworks for robotics and automation with advanced task scheduling techniques. International Journal of Engineering Research & Science Technology, 2347–3657.

Gudivaka, R. K., Gudivaka, R. L., & Gudivaka, B. R. (2019). Robotics-Driven Swarm Intelligence for Adaptive and Resilient Pandemic Alleviation in Urban Ecosystems. International Journal of Modern Electronics and Communication Engineering, 2321- 2152.

Downloads

Published

2026-04-06