Abstract

Multi-cloud deployments face significant security challenges due to fragmented visibility and regulatory constraints on data sharing. This paper proposes a novel Federated Learning (FL) framework for privacy-preserving anomaly detection across heterogeneous cloud environments. The proposed approach combines adaptive federated aggregation (AFA) with a hybrid CNN-LSTM model, differential privacy, and homomorphic encryption to address non-IID data distributions, communication overhead, and privacy risks. Evaluations using synthesized AWS, Azure, and GCP workload traces demonstrate 92.3% F1-score (13.7% improvement over FedAvg) while reducing communication overhead by 63% and resisting model inversion attacks with ε=1.0 differential privacy. The framework maintains compliance with GDPR/HIPAA by design, eliminating raw data transmission. Comparative analysis reveals 28% faster convergence than centralized approaches in asymmetric network conditions, establishing FL as a viable paradigm for cross-cloud security analytics.

References

• Ahn, J., Lee, Y., Kim, N., Park, C., & Jeong, J. (2023). Federated learning for predictive maintenance and anomaly detection using time series data distribution shifts in manufacturing processes. Sensors, 23(17), 7331. https://doi.org/10.3390/s23177331
• Chen, Z., et al. (2023). FedLGAN: A method for anomaly detection and repair of hydrological telemetry data based on federated learning. PeerJ Computer Science, 9, e1664. https://doi.org/10.7717/peerj-cs.1664
• Huong, T. T., Bac, T. P., Quang, L. A., Dan, N. M., Cong, L. T., & Hung, N. T. (2022). Light-weight federated learning-based anomaly detection for time-series data in industrial control systems. Computers in Industry, 140, 103692. https://doi.org/10.1016/j.compind.2022.103692
• Kim, J., Lee, S., et al. (2023). Enhancing anomaly detection in distributed power systems using autoencoder-based federated learning. PLoS ONE, 18(8), e0290337. https://doi.org/10.1371/journal.pone.0290337
• Liu, Y., Garg, S., Nie, J., Zhang, Y., Xiong, Z., Kang, J., & Hossain, M. S. (2020). 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), 6348–6358. https://doi.org/10.1109/JIOT.2020.3011726
• Marfo, W., et al. (2023). Network anomaly detection using federated learning. IEEE Transactions on Network and Service Management, 20(3), 1234–1245. https://doi.org/10.1109/TNSM.2023.3261234
• Nguyen, T. D., et al. (2021). Federated learning for anomaly-based intrusion detection. IEEE Access, 9, 74720–74733. https://doi.org/10.1109/ACCESS.2021.3071234
• Preuveneers, D., Rimmer, V., Tsingenopoulos, I., Spooren, J., Joosen, W., & Ilie-Zudor, E. (2018). Chained anomaly detection models for federated learning: An intrusion detection case study. Applied Sciences, 8(12), 2663. https://doi.org/10.3390/app8122663
• Sharma, R. K., et al. (2021). A federated learning approach to anomaly detection in smart buildings. ACM Transactions on Internet of Things, 2(3), 1–24. https://doi.org/10.1145/3467981
• Shin, T.-H., & Kim, S.-H. (2023). Utility analysis about log data anomaly detection based on federated learning.
• Applied Sciences, 13(7), 4495. https://doi.org/10.3390/app13074495
• Wang, X., Wang, Y., Javaheri, Z., Almutairi, L., Moghadamnejad, N., & Younes, O. S. (2023). Federated deep learning for anomaly detection in the internet of things. Computers & Electrical Engineering, 108651. https://doi.org/10.1016/j.compeleceng.2023.108651
• Zhou, Y., Wang, R., Mo, X., Li, Z., & Tang, T. (2023). Robust hierarchical federated learning with anomaly detection in cloud-edge-end cooperation networks. Electronics, 12(1), 112. https://doi.org/10.3390/electronics12010112