Federated Learning-Based Anomaly Detection for Privacy-Preserving Cloud Security
DOI:
https://doi.org/10.63345/sjaibt.v2.i1.302Keywords:
Federated Learning, Anomaly Detection, Privacy, Cloud, SecurityAbstract
The exponential growth of cloud computing has made robust anomaly and intrusion detection systems critical for safeguarding enterprise infrastructure. However, traditional centralized security architectures rely on aggregating massive volumes of raw network logs onto a single server, posing severe privacy risks, regulatory compliance challenges, and significant bandwidth overhead. As cyber threats become more sophisticated, the necessity to analyze distributed cloud traffic without exposing sensitive proprietary data or creating a vulnerable single point of failure has driven the demand for novel, privacy-preserving security paradigms.
To address these challenges, this paper introduces a Federated Learning-Based Anomaly Detection framework designed specifically for multi-tenant cloud environments. Our decentralized approach enables multiple cloud nodes to collaboratively train a robust, global Deep Learning intrusion detection model by exchanging only privacy-enhanced parameter updates, ensuring raw data never leaves its local origin. Experimental evaluation utilizing the CIC-IDS2017 dataset demonstrates that our proposed federated model achieves over 97% detection accuracy—closely matching centralized baselines—while substantially reducing data transmission volumes and strictly preserving data confidentiality across distributed cloud networks.
Downloads
References
[1]. Gayathri, S., and D. Surendran. "Unified ensemble federated learning with cloud computing for online anomaly detection in energy-efficient wireless sensor networks." Journal of cloud computing 13.1 (2024): 49.
[2]. Cui, Lei, et al. "Security and privacy-enhanced federated learning for anomaly detection in IoT infrastructures." IEEE Transactions on Industrial Informatics 18.5 (2021): 3492-3500.
[3]. Mothukuri, Viraaji, et al. "Federated-learning-based anomaly detection for IoT security attacks." IEEE Internet of Things Journal 9.4 (2021): 2545-2554.
[4]. Jithish, J., et al. "Distributed anomaly detection in smart grids: a federated learning-based approach." IEEE Access 11 (2023): 7157-7179.
[5]. Shrestha, Rakesh, et al. "Anomaly detection based on LSTM and autoencoders using federated learning in smart electric grid." Journal of Parallel and Distributed Computing 193 (2024): 104951.
[6]. Sater, Raed Abdel, and A. Ben Hamza. "A federated learning approach to anomaly detection in smart buildings." ACM Transactions on Internet of Things 2.4 (2021): 1-23.
[7]. Zhang, Chang, et al. "Anomaly detection and defense techniques in federated learning: a comprehensive review." Artificial Intelligence Review 57.6 (2024).
[8]. Liu, Yi, et al. "Deep anomaly detection for time-series data in industrial IoT: A communication-efficient on-device federated learning approach." IEEE Internet of Things Journal 8.8 (2020): 6348-6358.
[9]. C. Mavani, H. Mistry, A. M. Goswami, S. Tiwari, S. Pandey, and K. Kaushik, “Adversarially-Robust Federated Learning for Intrusion Detection in Decentralized Cyber-Physical Systems,” 2025 International Conference on Electrical, Communication, and Computing Technologies (iCONECCT), Gwalior, India, 2025, pp. 1–7, doi: 10.1109/iCONECCT67014.2025.11470195.
[10]. Ma, Shiyao, et al. "Privacy-preserving anomaly detection in cloud manufacturing via federated transformer." IEEE Transactions on Industrial Informatics 18.12 (2022): 8977-8987.
[11]. Wang, Xiaoding, et al. "Toward accurate anomaly detection in industrial internet of things using hierarchical federated learning." IEEE Internet of Things Journal 9.10 (2021): 7110-7119.
[12]. Gupta, Deepti, et al. "Hierarchical federated learning-based anomaly detection using digital twins for smart healthcare." 2021 IEEE 7th international conference on collaboration and internet computing (CIC). IEEE, 2021.
[13]. Priyadarshini, Ishaani. "Anomaly detection of IoT cyberattacks in smart cities using federated learning and split learning." Big Data and Cognitive Computing 8.3 (2024): 21.
[14]. Panga, Naresh Kumar Reddy, and M. Thanjaivadivel. "Adaptive DBSCAN and Federated Learning-Based Anomaly Detection for Resilient Intrusion Detection in Internet of Things Networks." International Journal of Management Research and Business Strategy 10.4 (2020): 39-56.
[15]. Nagamani, G. Muni, and Chanumolu Kiran Kumar. "Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning." Heliyon 10.24 (2024).
[16]. Zhang, Yixuan, et al. "Privacy-aware anomaly detection in IoT environments using FedGroup: A group-based federated learning approach." Journal of network and systems management 32.1 (2024): 20.
[17]. Dong, Boyu, et al. "FADngs: Federated learning for anomaly detection." IEEE Transactions on Neural Networks and Learning Systems 36.2 (2024): 2578-2592.
[18]. Huong, Truong Thu, et al. "Federated learning-based explainable anomaly detection for industrial control systems." IEEE Access 10 (2022): 53854-53872.
[19]. Kumar, KP Sanal, et al. "Security and privacy-aware artificial intrusion detection system using federated machine learning." Computers & Electrical Engineering 96 (2021): 107440.
[20]. Zhou, Yujie, et al. "Robust hierarchical federated learning with anomaly detection in cloud-edge-end cooperation networks." Electronics 12.1 (2022): 112.
[21]. Guo, Yalan, et al. "Anomaly detection using distributed log data: A lightweight federated learning approach." 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 2021.
[22]. C. Mavani, H. Mistry, A. M. Goswami, S. Tiwari, S. Pandey, and K. Kaushik, “Adversarially-Robust Federated Learning for Intrusion Detection in Decentralized Cyber-Physical Systems,” 2025 International Conference on Electrical, Communication, and Computing Technologies (iCONECCT), Gwalior, India, 2025, pp. 1–7, doi: 10.1109/iCONECCT67014.2025.11470195.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of Artificial Intelligence and Blockchain Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The license allows re-users to share and adapt the work, as long as credit is given to the author and don't use it for commercial purposes.
