FedSA: Arrefecimento Simulado Federado para a Aceleração da Detecção de Intrusão em Ambientes Colaborativos

• Helio N. C. Neto UFF
• Diogo M. F. Mattos UFF
• Natalia C. Fernandes UFF

DOI: https://doi.org/10.5753/sbrc.2021.16727

Abstract

Federated learning-based intrusion detection systems (IDS) train a global model with participants collaboration, who train local models based on machine learning. Optimization challenges, implicit in federated learning scenarios, are related to heterogeneity and imbalance in data distribution among participants. This paper proposes the Federated Simulated Annealing (FedSA) aggregation algorithm to select the hyperparameters and the participant's selection for each global aggregation rounds in federated learning. The adapted Federated Simulated Annealing participant's selection and hyperparameters selection reduces the iteration number and speeds up convergence. Thus, promoting rapid dissemination of new learnings extracted from the local models. The proposed assessment in a federated intrusion detection system scenario shows that the global model using FedSA converges in just ten global iterations. In comparison, the traditional algorithm requires twenty iterations for both to achieve 99.8% accuracy in Detecting Attacks.

References

Andreoni Lopez, M., Mattos, D. M., Duarte, O. C. M. e Pujolle, G. (2019). Toward a monitoring and threat detection system based on stream processing as a virtual network function for big data. Concurrency and Computation: Practice and Experience, 31(20):e5344.

Brendan McMahan, H., Moore, E., Ramage, D., Hampson, S. e Agüera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. Em Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, volume 54.

Corinzia, L. e Buhmann, J. M. (2019). Variational federated multi-task learning. arXiv preprint arXiv:1906.06268.

Cunha Neto, H. N., Mattos, D. M. F. e Fernandes, N. C. (2020). Privacidade do usuário em aprendizado colaborativo: Federated learning, da teoria à prática. Minicursos do Simpósio Brasileiro de Segurança de Informação e de Sistemas Computacionais SBSeg, 20:142–195.

de Souza, L. A. C., Antonio F. Rebello, G., Camilo, G. F., Guimarães, L. C. B. e Duarte, O. C. M. B. (2020). Dfedforest: Decentralized federated forest. Em 2020 IEEE International Conference on Blockchain (Blockchain), p. 90–97.

Guimarães, L. C. B., Rebello, G. A. F., Fernandes, F. S., Camilo, G. F., de Souza, L. A. C., dos Santos, D. C., de Oliveira, L. G. C. M. e Duarte, O. C. M. B. (2020). Temiant: Threat monitoring and intelligent data analytics of network traffic. Em 2020 4th Conference on Cloud and Internet of Things (CIoT), p. 9–16.

Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y. C., Yang, Q., Niyato, D. e Miao, C. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys Tutorials.

Liu, H. e Lang, B. (2019). Machine learning and deep learning methods for intrusion detection systems: A survey. applied sciences, 9(20):4396.

Nguyen, T. D., Marchal, S., Miettinen, M., Fereidooni, H., Asokan, N. e Sadeghi, A. (2019). D¨Iot: A federated self-learning anomaly detection system for iot. Em 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), p. 756–767.

Preuveneers, D., Rimmer, V., Tsingenopoulos, I., Spooren, J., Joosen, W. e Ilie-Zudor, E. (2018). Chained anomaly detection models for federated learning: An intrusion detection case study. Applied Sciences, 8(12):2663.

Reis, L. H. A., Murillo Piedrahita, A., Rueda, S., Fernandes, N. C., Medeiros, D. S. V., de Amorim, M. D. e Mattos, D. M. F. (2020). Unsupervised and incremental learning orchestration for cyber-physical security. Transactions on Emerging Telecommunications Technologies, 31(7):e4011.

Sharafaldin, I., Lashkari, A. H., Hakak, S. e Ghorbani, A. A. (2019). Developing realistic distributed denial of service (ddos) attack dataset and taxonomy. Em 2019 International Carnahan Conference on Security Technology (ICCST), p. 1–8.

Silva, J. V. V., Lopez, M. A. e Mattos, D. M. F. (2020). Attackers are not stealthy: Statistical analysis of the well-known and infamous kdd network security dataset. Em 2020 4th Conference on Cloud and Internet of Things (CIoT), p. 1–8.

Smith, V., Chiang, C.-K., Sanjabi, M. e Talwalkar, A. S. (2017). Federated multi-task learning. Em Advances in Neural Information Processing Systems, p. 4424–4434.

Van Laarhoven, P. J. e Aarts, E. H. (1987). Simulated annealing. Em Simulated annealing: Theory and applications, p. 7–15. Springer.

Viegas, E., Santin, A., Bessani, A. e Neves, N. (2019). Bigow: Real-time and reliable anomaly-based intrusion detection for high-speed networks. Future Generation Computer Systems, 93:473 – 485.

Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T. e Chan, K. (2019). Adaptive Federated Learning in Resource Constrained Edge Computing Systems. IEEE Journal on Selected Areas in Communications, 37(6):1205–1221.