Federated Learning-Based Secure Intrusion Detection Framework for Edge-IoT Communication Systems
DOI:
https://doi.org/10.59992/IJCI.2026.v5n6p2Keywords:
Autoencoders, Edge Computing, Federated Learning, Intrusion Detection Systems, Internet of ThingsAbstract
The advent of Edge-Internet of Things (Edge-IoT) communication systems has created a huge cyber security problem with connected devices being heterogeneous, distributed and resource constrained. Centralized intrusion detection systems (IDSs) tend to be data-hungry, impose significant communications overhead, add latency, and have serious privacy concerns. However, due to these limitations, this paper suggests an Edge-IoT Communication Systems Federated Learning-Based Secure Intrusion Detection Framework which facilitates collaborative and secure detection of cyberattacks without sharing raw data from the network. The proposed system includes federated learning systems to enable local ID models training at edge nodes, and distributed edge intelligence to send only encrypted model parameters to a central coordinator. The architecture is built to be used in smart home, smart healthcare, and industrial IoT applications that allow for both the scalable and decentralized cybersecurity operations. It uses a set of deep learning-based IDS models like Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid autoencoder architectures to identify several cyber threats, including distributed denial of service (DDoS) attacks, botnets, spoofing attacks, ransomware traffic, and abnormal communication behavior. It also includes differential privacy and secure aggregation techniques to ensure privacy and security in local model updates from users, mitigating the risk of inference attacks and unauthorized access. Experimental analysis is conducted using CICIDS2017 dataset and the results show that the proposed federated framework outperforms the centralized IDS and traditional machine learning techniques in terms of high IDS accuracy, low false alarm rates, less communication overhead, and privacy preservation. The findings suggest that the proposed framework offers an efficient, scalable, and lightweight cybersecurity solution for next-generation Edge-IoT communication systems without compromising the information security and adaptive threat intelligence.
References
• Alhawas, S., & Rassam, M. A. (2026). Federated Learning in Edge Computing: Vulnerabilities, Attacks, and Defenses—A Survey. Sensors (Basel, Switzerland), 26(4), 1275.
• Alshahrani, H., Alrowais, F., Alghamdi, M. H., Alqahtani, M., Asklany, S. A., Alymani, M., ... & Marzouk, R. (2025). Edge‐Driven Federated Learning Approach for Distributed Assault Monitoring in Vehicular Networks. Transactions on Emerging Telecommunications Technologies, 36(12), e70311.
• Anwer, R. W., Abrar, M., Ullah, M., Salam, A., & Ullah, F. (2025). Advanced intrusion detection in the industrial internet of things using federated learning and LSTM models. Ad Hoc Networks, 103991.
• Asiri, F., Malwi, W. A., Masood, F., Alshehri, M. S., Zhukabayeva, T., Shah, S. A., & Ahmad, J. (2025). Privacy Preserving Federated Anomaly Detection in IoT Edge Computing Using Bayesian Game Reinforcement Learning. Computers, Materials & Continua, 84(2).
• Awan, K. A., Din, I. U., Zareei, M., Almogren, A., Seo-Kim, B., & Pérez-Díaz, J. A. (2023). Securing iot with deep federated learning: A trust-based malicious node identification approach. IEEE Access, 11, 58901-58914.
• Babar, M., Khan, Z., Kaleem, S., Qureshi, B., & Boulila, W. (2026). TAWB-SFL: Trust-Aware Blockchain-Orchestrated Split Federated Learning for Intrusion Detection in 6G Healthcare IoT. IEEE Open Journal of the Communications Society.
• Benameur, R., & Dahane, A. (2025). Sfedrl-ids: secure federated deep reinforcement learning-based intrusion detection system for agricultural internet of things. Cluster Computing, 28(6), 403.
• Bukhari, S. M. S., Zafar, M. H., Abou Houran, M., Qadir, Z., Moosavi, S. K. R., & Sanfilippo, F. (2024). Enhancing cybersecurity in Edge IIoT networks: An asynchronous federated learning approach with a deep hybrid detection model. Internet of Things, 27, 101252.
• Driss, M., Almomani, I., e Huma, Z., & Ahmad, J. (2022). A federated learning framework for cyberattack detection in vehicular sensor networks. Complex & Intelligent Systems, 8(5), 4221-4235.
• Fadaei, A., & Barekatain, B. (2026). A novel intrusion detection system for dew computing environments based on an enhanced federated deep learning model. The Journal of Supercomputing, 82(3), 172.
• Gosai, K., Vaghela, H., Prajapati, Y., & Suthar, O. P. (2026). Federated Learning for Intrusion Detection in Edge Computing for Cloud IoT Systems. Strategic Approaches to Intrusion Detection in Cloud‐IoT Ecosystem, 251-282.
• Hajla, S. E., Ennaji, E. M., Maleh, Y., & Mounir, S. (2025). HFEL: A hybrid federated ensemble learning framework for intrusion detection in IoT networks. Cluster Computing, 28(13), 819.
• Kushwaha, V. K., Verma, D. K., Yadav, S. P., & Gupta, H. (2026). Energy-Aware Federated Learning for IoT Intrusion Detection Using Latent Feature Encoding. IEEE Access.
• Li, H., Ge, L., & Tian, L. (2024). Survey: federated learning data security and privacy-preserving in edge-Internet of Things. Artificial Intelligence Review, 57(5), 130.
• Liang, Y., & Luo, M. (2026). Optimization of distributed network intrusion detection system based on internet of things and federated learning. Discover Internet of Things, 6(1), 3.
• Lilhore, U. K., Sharma, Y. K., Pradeep, S., Rubaiee, S., Alroobaea, R., Baqasah, A. M., ... & Tekeste, L. G. (2026). Blockchain-enabled federated learning framework with hybrid CNN-LSTM anomaly detection for secure edge IoT networks. Journal of Cloud Computing.
• Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. V. (2021). Federated learning for internet of things: A comprehensive survey. IEEE communications surveys & tutorials, 23(3), 1622-1658.
• Popoola, S. I., Ande, R., Adebisi, B., Gui, G., Hammoudeh, M., & Jogunola, O. (2021). Federated deep learning for zero-day botnet attack detection in IoT-edge devices. IEEE Internet of Things Journal, 9(5), 3930-3944.
• Regan, C., Nasajpour, M., Parizi, R. M., Pouriyeh, S., Dehghantanha, A., & Choo, K. K. R. (2022). Federated IoT attack detection using decentralized edge data. Machine Learning with Applications, 8, 100263.
• Reis, M. J. (2025). Edge-FLGuard+: a federated and lightweight anomaly detection framework for securing 5G-enabled IoT in smart homes. Future Internet, 17(8), 329.
• Rezaei, H., Taheri, R., Nowroozi, E., Hajizadeh, M., Shiaeles, S., & Bauschert, T. (2025). A Survey on Security and Privacy in Federated Learning-Based Intrusion Detection Systems for 5G and Beyond Networks. IEEE Open Journal of the Communications Society, 7, 253-300.
• Riyadi, M. A. Q., & Dewi, A. M. (2026). Federated Learning for Privacy-Preserving IoT Intrusion Detection under Extreme Non-IID Conditions. Jurnal Ilmu Komputer dan Informasi, 19(1), 107-120.
• Satyanarayana, P., Mohan, D., Matta, P. R., Rao, G. P., & Krishnan, V. G. (2026, March). Secure Artificial Intelligence Systems for Edge-IoT Environments Using Federated Learning. In 2026 3rd International Conference on Emerging Trends in Engineering and Medical Sciences (ICETEMS) (pp. 1-6). IEEE.
• Selvam, P., Karthikeyan, P., Manochitra, S., Sujith, A. V. L. N., Ganesan, T., Ayyasamy, R., ... & Rajendran, A. (2025). Federated learning-based hybrid convolutional recurrent neural network for multi-class intrusion detection in IoT networks. Discover Internet of Things, 5(1), 39.
• Sharma, D., Singh, J., & Bhambri, P. (2025, October). Federated Learning for Intrusion Detection in IoT Networks: A Comprehensive Review. In 2025 2nd International Conference on Electronic Circuits and Signaling Technologies (ICECST) (pp. 614-619). IEEE.
• Singh, A., Chatterjee, K., & Satapathy, S. C. (2022). An edge based hybrid intrusion detection framework for mobile edge computing. Complex & Intelligent Systems, 8(5), 3719-3746.
• Soomro, I. A., Rehman, H. U., Hussain, S. J., Latif, S., Mujlid, H., Mohsin, S. M., & Maple, C. (2025). ROCHE: A Robust and End-to-End Privacy-Preserving Federated Learning Framework for Intrusion Detection in Industrial Internet of Things. IEEE Internet of Things Journal.
• Swathi, K., Durga, P., Prasad, K. V., Chaitanya, A. K., Santhi, K., Vidyullatha, P., & Rao, S. V. A. (2025). Secure blockchain integrated deep learning framework for federated risk-adaptive and privacy-preserving IoT edge intelligence sets. Scientific Reports, 15(1), 41133.
• Torre, D., Chennamaneni, A., Jo, J., Vyas, G., & Sabrsula, B. (2025). Toward enhancing privacy preservation of a federated learning cnn intrusion detection system in iot: Method and empirical study. ACM Transactions on Software Engineering and Methodology, 34(2), 1-48.
