Provimento de Privacidade na Detecção de Anomalias na O-RAN
Resumo
A arquitetura Open Radio Access Network (O-RAN) promete transformar a comunicação sem fio ao permitir gestão inteligente da rede por meio de aplicativos de terceiros, conhecidos como xApps e rApps. Contudo, estes aplicativos acessam dados sensíveis da rede e dos usuários, criando riscos de privacidade e segurança. Ao mesmo tempo, a detecção de anomalias é essencial para garantir desempenho confiável e segurança da O-RAN. Nesse contexto, este artigo propõe uma solução de detecção de anomalias com preservação de privacidade para a O-RAN, através da utilização de Fully Homomorphic Encryption (FHE) para ocultar dados sensíveis antes de serem acessados por xApps de terceiros. Os resultados experimentais mostram que, embora a FHE cause sobrecarga computacional, a latência de inferência continua adequada para o ciclo de controle do O-RAN. Além disso, a acurácia do modelo não é afetada, demonstrando que a FHE é uma alternativa viável para construir inteligência segura e confiável na O-RAN.Referências
Acar, A., Aksu, H., Uluagac, A. S., and Conti, M. (2018). A survey on homomorphic encryption schemes: Theory and implementation. ACM Comput. Surv., 51(4).
Cheon, J. H., Kim, A., Kim, M., and Song, Y. (2016). Homomorphic encryption for arithmetic of approximate numbers. Cryptology ePrint Archive, Paper 2016/421.
Chiejina, A., Kim, B., Chowhdury, K., and Shah, V. K. (2024). System-level analysis of adversarial attacks and defenses on intelligence in o-ran based cellular networks. In 17th ACM Conference on Security and Privacy in Wireless and Mobile Networks.
Dias, V., Silva, M., Gomes, M., Oliveira, L., Riker, A., and Abelém, A. (2024). Mitigação inteligente de ataques DDoS em redes o-RAN utilizando aprendizado de máquina. In XV Workshop de Pesquisa Experimental da Internet do Futuro, pages 55–62. SBC.
Dryjanski, M., Kulacz, L., and Kliks, A. (2021). Toward modular and flexible open ran implementations in 6g networks: Traffic steering use case and o-ran xapps. Sensors.
Fan, J. and Vercauteren, F. (2012). Somewhat practical fully homomorphic encryption. Cryptology ePrint Archive, Paper 2012/144.
Frery, J., Stoian, A., Bredehoft, R., Montero, L., Kherfallah, C., Chevallier-Mames, B., and Meyre, A. (2023). Privacy-preserving tree-based inference with fully homomorphic encryption. Published: Cryptology ePrint Archive, Paper 2023/258.
Grinsztajn, L., Oyallon, E., and Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems, 35:507–520.
Kaltenberger, F., De Souza, G., Knopp, R., and Wang, H. (2019). The OpenAirInterface 5g new radio implementation: Current status and roadmap. In 23rd ITG Workshop on Smart Antennas, Demo Session.
Khan, M. S., Farzaneh, B., Shahriar, N., Saha, N., and Boutaba, R. (2022). SliceSecure: Impact and detection of DoS/DDoS attacks on 5g network slices. In 2022 IEEE Future Networks World Forum (FNWF), pages 639–642. IEEE Computer Society.
Lacava, A., Polese, M., Sivaraj, R., Soundrarajan, R., Bhati, B. S., Singh, T., Zugno, T., Cuomo, F., and Melodia, T. (2023). Programmable and customized intelligence for traffic steering in 5g networks using open ran architectures. IEEE Transactions on Mobile Computing, 23(4):2882–2897.
Lin, D., Bhargav, S., Chiejina, A., Ibrahem, M. I., and Shah, V. K. (2025). Zt-ric: A zero trust ric framework for ensuring data privacy and confidentiality in open ran. In IEEE 22nd Consumer Communications & Networking Conference (CCNC).
Louppe, G. (2014). Understanding random forests: From theory to practice. Universite de Liege (Belgium).
Luay, M., Layeghy, S., Hosseininoorbin, S., Sarhan, M., Moustafa, N., and Portmann, M. (2025). Temporal analysis of NetFlow datasets for network intrusion detection systems. In [link].
O-RAN ALLIANCE (2022). O-RAN.WG1.O-RAN-Architecture-Description-v07.00. Technical Specification 7, O-RAN ALLIANCE.
Obeidat, I., Hamadneh, N., Al-kasassbeh, M., and Almseidin, M. (2018). Intensive preprocessing of KDD cup 99 for network intrusion classification using machine learning techniques. arXiv preprint arXiv:1805.10458.
Oseledets, I. V. and Tyrtyshnikov, E. E. (2009). Breaking the curse of dimensionality, or how to use svd in many dimensions. SIAM Journal on Scientific Computing, 31(5):3744–3759.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., and Melodia, T. (2023). Understanding o-RAN: Architecture, interfaces, algorithms, security, and research challenges. IEEE Communications Surveys & Tutorials, 25(2):1376–1411.
Schmidt, R., Irazabal, M., and Nikaein, N. (2021). FlexRIC: an SDK for next-generation SD-RANs. In Proceedings of the 17th International Conference on Emerging Networking EXperiments and Technologies, CoNEXT ’21, pages 411–425.
Tsourdinis, T., Makris, N., Korakis, T., and Fdida, S. (2024). AI-driven network intrusion detection and resource allocation in real-world o-RAN 5g networks. In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking.
Xavier, B. M., Dzaferagic, M., Collins, D., Comarela, G., Martinello, M., and Ruffini, M. (2023). Machine learning-based early attack detection using open ran intelligent controller. In ICC 2023-IEEE International Conference on Communications.
Zama (2022). Concrete ML: a privacy-preserving machine learning library using fully homomorphic encryption for data scientists. In [link].
Cheon, J. H., Kim, A., Kim, M., and Song, Y. (2016). Homomorphic encryption for arithmetic of approximate numbers. Cryptology ePrint Archive, Paper 2016/421.
Chiejina, A., Kim, B., Chowhdury, K., and Shah, V. K. (2024). System-level analysis of adversarial attacks and defenses on intelligence in o-ran based cellular networks. In 17th ACM Conference on Security and Privacy in Wireless and Mobile Networks.
Dias, V., Silva, M., Gomes, M., Oliveira, L., Riker, A., and Abelém, A. (2024). Mitigação inteligente de ataques DDoS em redes o-RAN utilizando aprendizado de máquina. In XV Workshop de Pesquisa Experimental da Internet do Futuro, pages 55–62. SBC.
Dryjanski, M., Kulacz, L., and Kliks, A. (2021). Toward modular and flexible open ran implementations in 6g networks: Traffic steering use case and o-ran xapps. Sensors.
Fan, J. and Vercauteren, F. (2012). Somewhat practical fully homomorphic encryption. Cryptology ePrint Archive, Paper 2012/144.
Frery, J., Stoian, A., Bredehoft, R., Montero, L., Kherfallah, C., Chevallier-Mames, B., and Meyre, A. (2023). Privacy-preserving tree-based inference with fully homomorphic encryption. Published: Cryptology ePrint Archive, Paper 2023/258.
Grinsztajn, L., Oyallon, E., and Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems, 35:507–520.
Kaltenberger, F., De Souza, G., Knopp, R., and Wang, H. (2019). The OpenAirInterface 5g new radio implementation: Current status and roadmap. In 23rd ITG Workshop on Smart Antennas, Demo Session.
Khan, M. S., Farzaneh, B., Shahriar, N., Saha, N., and Boutaba, R. (2022). SliceSecure: Impact and detection of DoS/DDoS attacks on 5g network slices. In 2022 IEEE Future Networks World Forum (FNWF), pages 639–642. IEEE Computer Society.
Lacava, A., Polese, M., Sivaraj, R., Soundrarajan, R., Bhati, B. S., Singh, T., Zugno, T., Cuomo, F., and Melodia, T. (2023). Programmable and customized intelligence for traffic steering in 5g networks using open ran architectures. IEEE Transactions on Mobile Computing, 23(4):2882–2897.
Lin, D., Bhargav, S., Chiejina, A., Ibrahem, M. I., and Shah, V. K. (2025). Zt-ric: A zero trust ric framework for ensuring data privacy and confidentiality in open ran. In IEEE 22nd Consumer Communications & Networking Conference (CCNC).
Louppe, G. (2014). Understanding random forests: From theory to practice. Universite de Liege (Belgium).
Luay, M., Layeghy, S., Hosseininoorbin, S., Sarhan, M., Moustafa, N., and Portmann, M. (2025). Temporal analysis of NetFlow datasets for network intrusion detection systems. In [link].
O-RAN ALLIANCE (2022). O-RAN.WG1.O-RAN-Architecture-Description-v07.00. Technical Specification 7, O-RAN ALLIANCE.
Obeidat, I., Hamadneh, N., Al-kasassbeh, M., and Almseidin, M. (2018). Intensive preprocessing of KDD cup 99 for network intrusion classification using machine learning techniques. arXiv preprint arXiv:1805.10458.
Oseledets, I. V. and Tyrtyshnikov, E. E. (2009). Breaking the curse of dimensionality, or how to use svd in many dimensions. SIAM Journal on Scientific Computing, 31(5):3744–3759.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., and Melodia, T. (2023). Understanding o-RAN: Architecture, interfaces, algorithms, security, and research challenges. IEEE Communications Surveys & Tutorials, 25(2):1376–1411.
Schmidt, R., Irazabal, M., and Nikaein, N. (2021). FlexRIC: an SDK for next-generation SD-RANs. In Proceedings of the 17th International Conference on Emerging Networking EXperiments and Technologies, CoNEXT ’21, pages 411–425.
Tsourdinis, T., Makris, N., Korakis, T., and Fdida, S. (2024). AI-driven network intrusion detection and resource allocation in real-world o-RAN 5g networks. In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking.
Xavier, B. M., Dzaferagic, M., Collins, D., Comarela, G., Martinello, M., and Ruffini, M. (2023). Machine learning-based early attack detection using open ran intelligent controller. In ICC 2023-IEEE International Conference on Communications.
Zama (2022). Concrete ML: a privacy-preserving machine learning library using fully homomorphic encryption for data scientists. In [link].
Publicado
25/05/2026
Como Citar
TOKARSKI, Thiago; ALCHIERI, Eduardo; BARRETO, Priscila Solis.
Provimento de Privacidade na Detecção de Anomalias na O-RAN. In: WORKSHOP DE TESTES E TOLERÂNCIA A FALHAS (WTF), 27. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 150-163.
ISSN 2595-2684.
DOI: https://doi.org/10.5753/wtf.2026.22948.
