F-NIDS – Sistema de Detecção de Intrusão descentralizado com base em Aprendizado Federado

• Jonathas A. de Oliveira UnB
• Rodolfo I. Meneguette USP
• Vinícius P. Gonçalves UnB
• Rafael T. de Sousa Jr. UnB
• Daniel L. Guidoni UFOP
• José C. M. Oliveira UESB
• Geraldo P. Rocha Filho UESB

DOI: https://doi.org/10.5753/sbrc.2023.426

Abstract

The coming of IoT networks introduced new scalability and security challenges due to the massive number of connections and higher data transferring rate in these networks. Although there have been efforts in recent years to mitigate these effects, there are still questions to be investigated, such as data privacy and scalability in distributed IoT scenarios. This work proposes the F-NIDS is an intrusion detector that uses federated artificial intelligence and differential privacy techniques, combined with asynchronous communication between system entities, aiming for scalability and data confidentiality. F-NIDS has an architecture proposal to allow usage in cloud or fog IoT environments. Results have shown that: the confidential detection model, used on F-NIDS, keeps satisfactory performance metrics and, in the event of an attack, predicts and determines the nature.

References

Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., and Zhang, L. (2016). Deep learning with differential privacy. page 308-318.

Al-Yaseen, W. L., Othman, Z. A., and Nazri, M. Z. A. (2017). Real-time multi-agent system for an adaptive intrusion detection system. Pattern Recognition Letters, 85:56-64.

Bu, Z., Dong, J., Long, Q., and Su, W. (2020). Deep Learning With Gaussian Differential Privacy. Harvard Data Science Review, 2(3). https://hdsr.mitpress.mit.edu/pub/u24wj42y.

Cavalcante, I. C., Meneguette, R. I., Torres, R. H., Mano, L. Y., Gonçalves, V. P., Ueyama, J., Pessin, G., Amvame Nze, G. D., and Rocha Filho, G. P. (2022). Federated system for transport mode detection. Energies, 15(23):9256.

Chaabouni, N., Mosbah, M., Zemmari, A., Sauvignac, C., and Faruki, P. (2019). Network intrusion detection for iot security based on learning techniques. IEEE Communications Surveys Tutorials, 21(3):2671-2701.

Chen, H., Hussain, S. U., Boemer, F., Stapf, E., Sadeghi, A. R., Koushanfar, F., and Cammarota, R. (2020). Developing privacy-preserving ai systems: The lessons learned. In 2020 57th ACM/IEEE Design Automation Conference (DAC), pages 1-4.

Dwork, C. (2006). Differential privacy. In Bugliesi, M., Preneel, B., Sassone, V., and Wegener, I., editors, Automata, Languages and Programming, pages 1-12, Berlin, Heidelberg. Springer Berlin Heidelberg.

Geraldo Filho, P., Villas, L. A., Gonçalves, V. P., Pessin, G., Loureiro, A. A., and Ueyama, J. (2019). Energy-efficient smart home systems: Infrastructure and decision-making process. Internet of Things, 5:153-167.

Habibzadeh, H., Nussbaum, B. H., Anjomshoa, F., Kantarci, B., and Soyata, T. (2019). A survey on cybersecurity, data privacy, and policy issues in cyber-physical system deployments in smart cities. Sustainable Cities and Society, 50:101660.

Kundu, A. (2021). Fed+: A unified approach to robust personalized federated learning.

M., R., Ahmed, M., and Khan, R. (2019). An adaptive distributed intrusion detection system architecture using multi agents. International Journal of Electrical and Computer Engineering (IJECE), 9:4951.

McMahan, B., Moore, E., Ramage, D., Hampson, S., and Arcas, B. A. y. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. In Singh, A. and Zhu, J., editors, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, volume 54 of Proceedings of Machine Learning Research, pages 1273-1282. PMLR.

Qian, B., Su, J., Wen, Z., Jha, D. N., Li, Y., Guan, Y., Puthal, D., James, P., Yang, R., Zomaya, A. Y., Rana, O., Wang, L., Koutny, M., and Ranjan, R. (2020). Orchestrating the development lifecycle of machine learning-based iot applications: A taxonomy and survey. ACM Comput. Surv., 53(4).

Rahman, M. A. and Asyhari, A. T. (2019). The emergence of internet of things (iot): Connecting anything, anywhere. Computers, 8(2).

Roman, R., Zhou, J., and Lopez, J. (2013). On the features and challenges of security and privacy in distributed internet of things. Computer Networks, 57(10):2266-2279. Towards a Science of Cyber Security Security and Identity Architecture for the Future Internet.

Ruzafa-Alcazar, P., Fernandez-Saura, P., Marmol-Campos, E., Gonzalez-Vidal, A., Hernandez Ramos, J. L., Bernal, J., and Skarmeta, A. F. (2021). Intrusion detection based on privacy-preserving federated learning for the industrial iot. IEEE Transactions on Industrial Informatics, pages 1-1.

Salem, A., Sautter, Y., Backes, M., Humbert, M., and Zhang, Y. (2020). Baaan: Backdoor attacks against autoencoder and gan-based machine learning models.

Sarhan, M., Layeghy, S., and Portmann, M. (2022). Towards a standard feature set for network intrusion detection system datasets. Mobile Networks and Applications, 27(1):357-370.

Tabassum, A., Erbad, A., Mohamed, A., and Guizani, M. (2021). Privacy-preserving distributed ids using incremental learning for iot health systems. IEEE Access, 9:14271-14283.

Zhao, R., Yin, Y., Shi, Y., and Xue, Z. (2020). Intelligent intrusion detection based on federated learning aided long short-term memory. Physical Communication, 42:101157.

Zhu, H., Zhang, H., and Jin, Y. (2021). From federated learning to federated neural architecture search: a survey. Complex & Intelligent Systems, 7.