Privacy Preserving Federated Intrusion Detection in Distributed Networks

Authors

DOI:

https://doi.org/10.68307/5ercgy27

Keywords:

Differential privacy, distributed networks, federated learning, intrusion detection, secure aggregation, traffic classification

Abstract

Collaborative network intrusion detection requires diverse training data while preserving organisational control over traffic records, therefore this study examines a federated detector that combines a convolutional recurrent classifier with update clipping and Gaussian perturbation alongside secure aggregation, using the original study tables to compare centralised training and ordinary federated averaging with the protected configuration on NSL-KDD and CICIDS2017, where reported protected model accuracies are 97.3% and 97.6% respectively compared with centralised accuracies of 98.6% and 99.1% and ordinary federated accuracies of 97.9% and 98.2%, while the reported communication totals increase from 142 MB to 148 MB corresponding to a calculated increase of approximately 4.23%, with the reported membership inference indicator decreasing from 34.1% to 9.7% although its attack definition and metric are unspecified, consequently these measurements provide descriptive evidence of a modest reported detection gap but do not establish statistical significance or a verified privacy guarantee, because run logs and the noise multiplier are unavailable and the corrected weighted aggregation formulation has not been rerun, while the accompanying analysis identifies the sensitivity and accounting conditions required to validate the target privacy budget before deployment claims can be justified.

Author Biographies

  • Mr. Ram Chouhan, SAGE University Bhopal

    Mr. Ram Kumar Chouhan is an M.Tech Scholar with research interests in Artificial Intelligence, Machine Learning, Data Science, Cybersecurity, and emerging computing technologies. He is actively engaged in academic research and explores innovative approaches for developing intelligent and technology-driven solutions.

  • Dr. Kirti Jain, SAGE University Bhopal

    Dr. Kirti Jain is associated with SAGE University, Bhopal. Her academic and research interests include Computer Science, Artificial Intelligence, Machine Learning, Data Science, and emerging technologies. She is actively involved in academic research, teaching, and research-oriented activities.

  • Mr. Mahesh kumar bagwani, SAGE University Bhopal

    Mr. Mahesh Kumar Bagwani is associated with SAGE University, Bhopal. His research interests include Cloud Computing, Artificial Intelligence, Machine Learning, Web Technologies, and emerging computing technologies. He is actively involved in academic research and technology-oriented projects.

References

[1] B. McMahan, E. Moore, D. Ramage, S. Hampson and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” AISTATS, PMLR 54, pp 1273–1282, 2017. Source

[2] P. Kairouz et al., “Advances and Open Problems in Federated Learning,” arXiv:1912.04977, 2019. Source

[3] L. Zhu, Z. Liu and S. Han, “Deep Leakage from Gradients,” NeurIPS, vol 32, 2019. Source

[4] J. Geiping, H. Bauermeister, H. Dröge and M. Moeller, “Inverting Gradients — How easy is it to break privacy in federated learning?,” NeurIPS, 2020. Source

[5] R. Shokri, M. Stronati, C. Song and V. Shmatikov, “Membership Inference Attacks against Machine Learning Models,” IEEE Symposium on Security and Privacy, 2017. Source

[6] N. Carlini, S. Chien, M. Nasr, S. Song, A. Terzis and F. Tramèr, “Membership Inference Attacks From First Principles,” IEEE Symposium on Security and Privacy, 2022. Source

[7] S. A. Rahman, H. Tout, C. Talhi and A. Mourad, “Internet of Things Intrusion Detection: Centralized, On-Device, or Federated Learning?,” IEEE Network, vol 34, no 6, 2020. Source

[8] T. D. Nguyen, S. Marchal, M. Miettinen, H. Fereidooni, N. Asokan and A. R. Sadeghi, “DÏoT: A Federated Self-learning Anomaly Detection System for IoT,” IEEE ICDCS, pp 756–767, 2019. Source

[9] B. Li, Y. Wu, J. Song, R. Lu, T. Li and L. Zhao, “DeepFed: Federated Deep Learning for Intrusion Detection in Industrial Cyber-Physical Systems,” IEEE Transactions on Industrial Informatics, vol 17, no 8, pp 5615–5624, 2021. Source

[10] C. Dwork and A. Roth, “The Algorithmic Foundations of Differential Privacy,” Foundations and Trends in Theoretical Computer Science, vol 9, pp 211–407, 2014. Source

[11] M. Abadi et al., “Deep Learning with Differential Privacy,” ACM CCS, pp 308–318, 2016. Source

[12] R. C. Geyer, T. Klein and M. Nabi, “Differentially Private Federated Learning: A Client Level Perspective,” arXiv:1712.07557, 2017. Source

[13] K. Bonawitz et al., “Practical Secure Aggregation for Privacy-Preserving Machine Learning,” ACM CCS, pp 1175–1191, 2017. Source

[14] P. Kairouz, Z. Liu and T. Steinke, “The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation,” ICML, PMLR 139, 2021. Source

[15] M. K. Bagwani, A. Gangwar, K. Vishwakarma and V. K. Tiwari, “Real-time signature-based detection and prevention of DDOS attacks in cloud environments,” International Journal of Science and Research Archive, vol 12, no 2, pp 2929–2935, 2024, doi: 10.30574/ijsra.2024.12.2.1608. Source

[16] A. Khare, N. Choudhary and M. K. Bagwani, “Trustworthy and Adaptive Intrusion Detection for Imbalanced IoT Traffic,” International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, vol 1, no 1, pp 80–86, 2026, doi: 10.68307/k9pxqe13. Source

[17] I. Mironov, “Rényi Differential Privacy,” IEEE Computer Security Foundations Symposium, 2017. Source

[18] T. M. H. Hsu, H. Qi and M. Brown, “Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification,” arXiv:1909.06335, 2019. Source

[19] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar and V. Smith, “Federated Optimization in Heterogeneous Networks,” Proceedings of MLSys, 2020. Source

[20] S. P. Karimireddy, S. Kale, M. Mohri, S. Reddi, S. Stich and A. T. Suresh, “SCAFFOLD: Stochastic Controlled Averaging for Federated Learning,” ICML, PMLR 119, pp 5132–5143, 2020. Source

[21] M. Noble, A. Bellet and A. Dieuleveut, “Differentially Private Federated Learning on Heterogeneous Data,” AISTATS, PMLR 151, pp 10110–10145, 2022. Source

[22] X. Li, M. Jiang, X. Zhang, M. Kamp and Q. Dou, “FedBN: Federated Learning on Non-IID Features via Local Batch Normalization,” ICLR, 2021. Source

[23] E. Bagdasaryan, A. Veit, Y. Hua, D. Estrin and V. Shmatikov, “How To Backdoor Federated Learning,” AISTATS, PMLR 108, pp 2938–2948, 2020. Source

[24] T. D. Nguyen et al., “FLAME: Taming Backdoors in Federated Learning,” USENIX Security, pp 1415–1432, 2022. Source

[25] M. Tavallaee, E. Bagheri, W. Lu and A. A. Ghorbani, “A Detailed Analysis of the KDD CUP 99 Data Set,” IEEE CISDA, pp 1–6, 2009; dataset documentation. Source

[26] I. Sharafaldin, A. H. Lashkari and A. A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization,” ICISSP, pp 108–116, 2018; dataset documentation. Source

[27] N. Moustafa and J. Slay, “UNSW-NB15: A Comprehensive Data Set for Network Intrusion Detection Systems,” MilCIS, pp 1–6, 2015; dataset documentation. Source

[28] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol 9, no 8, pp 1735–1780, 1997. Source

[29] X. Zhang, X. Chen, M. Hong, Z. S. Wu and J. Yi, “Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy,” ICML, PMLR 162, 2022. Source

[30] M. Bun and T. Steinke, “Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds,” arXiv:1605.02065, 2016. Source

[31] N. Truong, K. Sun, S. Wang, F. Guitton and Y. Guo, “Privacy Preservation in Federated Learning: An Insightful Survey from the GDPR Perspective,” Computers & Security, vol 110, article 102402, 2021. Source

[32] A. Cheng, P. Wang, X. S. Zhang and J. Cheng, “Differentially Private Federated Learning With Local Regularization and Sparsification,” IEEE/CVF CVPR, pp 10122–10131, 2022. Source

[33] N. A. Al-Athba Al-Marri, B. S. Ciftler and M. M. Abdallah, “Federated Mimic Learning for Privacy Preserving Intrusion Detection,” arXiv:2012.06974, 2020, Sections IV–V and conclusion. Source

[34] N. S. Alshammari, S. Mishra, M. Rathi, N. Goel and S. Tahzib, “SecureTrust-FL: trust-aware privacy-preserving federated learning for network intrusion detection,” Scientific Reports, vol 16, article 28050, 2026, Tables 4–5, doi: 10.1038/s41598-026-58383-4. Source

Downloads

Published

2026-10-19

Issue

Section

Original Research Articles

How to Cite

Privacy Preserving Federated Intrusion Detection in Distributed Networks. (2026). IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, 1(2), 18-30. https://doi.org/10.68307/5ercgy27