TOFL: Time Optimized Federated Learning
Resumo
As redes veiculares enfrentam ameaças cibernéticas que podem prejudicar motoristas, passageiros e pedestres. Nesse cenário, uma possível solução para treinar modelos que detectem ameaças, sem violação da privacidade dos usuários, é o aprendizado federado. No entanto, o aprendizado federado é particularmente sensível a atrasos de comunicação, sendo esta uma consequência natural da alta mobilidade em redes veiculares. Tal problema é comumente ignorado pela literatura, que não considera a possibilidade de desconexões na rede. Este trabalho propõe uma estratégia de seleção de clientes projetada para minimizar o tempo de treinamento de um modelo de aprendizado de máquina para detecção de ameaças veiculares, considerando o tempo de comunicação que varia de acordo com a movimentação dos clientes. Os resultados demonstram que o TOFL, utilizando apenas 20% do total de clientes disponíveis, pode reduzir o tempo necessário para atingir alta acurácia em até 50% em comparação com abordagens do estado da arte, ao mesmo tempo que diminui o consumo de recursos dos dispositivos clientes.
Referências
Boualouache, A. e Engel, T. (2022). Federated Learning-based Scheme for Detecting Passive Mobile Attackers in 5G Vehicular Edge Computing. Annals of Telecommunications, páginas 1–20.
Boualouache, A. et al. (2023). 5g vehicle-to-everything at the cross-borders: Security challenges and opportunities. Internet of Things Magazine, 6(1):114–119.
Bousalem, B., Sakka, M. A., Silva, V. F., Jaafar, W., Letaifa, A. B. e Langar, R. (2023). DDoS Attacks Mitigation in 5G-V2X Networks: A Reinforcement Learning-Based Approach. Em International Conference on Network and Service Management (CNSM), páginas 1–5. IEEE.
Buyukates, B. e Ulukus, S. (2021). Timely Communication in Federated Learning. Em International Conference on Computer Communications Workshops (INFOCOM WKSHPS), páginas 1–6. IEEE.
Chatzoulis, D. et al. (2023). 5G V2X Performance Comparison for Different Channel Coding Schemes and Propagation Models. Sensors, 23(5):2436.
Committee, S. S. J. S. I. D. et al. (2016). Dedicated Short Range Communications (DSRC) Message set Dictionary. SAE International.
De Souza, L. A. C., Camilo, G. F., Rebello, G. A. F., Guimaraes, L. C., Campista, M. E. M. e Costa, L. H. M. K. (2024). Blockchain-based Approaches for Secure Federated Learning. Em 2024 6th Conference on Blockchain Research & Applications for Innovative Networks and Services (BRAINS), páginas 1–4. IEEE.
de Souza, L. A. C., Camilo, G. F., Rebello, G. A. F., Sammarco, M., Campista, M. E. M. e Costa, L. H. M. (2024). ATHENA-FL: Avoiding Statistical Heterogeneity with One-versus-All in Federated Learning. Journal of Internet Services and Applications, 15(1):273–288.
do Couto Teixeira, D., Almeida, J. M. e Viana, A. C. (2021). On Estimating the Predictability of Human Mobility: The Role of Routine. EPJ Data Science, 10(1):49.
ETSI (2014a). Intelligent Transport Systems (ITS); Vehicular Communications; Basic Set of Applications; Part 2: Specification of Cooperative Awareness Basic Service. ETSI.
ETSI (2014b). Intelligent Transport Systems (ITS); Vehicular Communications; Basic Set of Applications; Part 3: Specifications of Decentralized Environmental Notification Basic Service . ETSI.
Fittipaldi, G., Couto, R. S. e Costa, L. H. (2025). Exploring Traffic Pattern Variability in Vehicular Federated Learning. Computer Communications, página 108279.
Gong, B., Xing, T., Liu, Z., Xi, W. e Chen, X. (2022). Adaptive Client Clustering for Efficient Federated Learning over Non-IID and Imbalanced Data. Transactions on Big Data.
Gonzalez, M. C., Hidalgo, C. A. e Barabasi, A.-L. (2008). Understanding Individual Human Mobility Patterns. Nature, 453(7196):779–782.
Guimaraes, L. C., Rebello, G. A. F., Camilo, G. F., de Souza, L. A. C. e Duarte, O. C. M. (2022). A Threat Monitoring System for Intelligent Data Analytics of Network Traffic. Annals of Telecommunications, 77(7):539–554.
Kamel, J., Wolf, M., Van Der Hei, R. W., Kaiser, A., Urien, P. e Kargl, F. (2020). VeReMi Extension: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs. Em International Conference on Communications (ICC), páginas 1–6. IEEE.
Korba, A. A. et al. (2023). Federated Learning for Zero-Day Attack Detection in 5G and Beyond V2X Networks. Em International Conference on Communications (ICC). IEEE.
Luo, B., Xiao, W., Wang, S., Huang, J. e Tassiulas, L. (2022). Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling. Em Conference on Computer Communications (INFOCOM), páginas 1739–1748. IEEE.
McMahan, B. et al. (2017). Communication-efficient Learning of Deep Networks from Decentralized Data. Artificial Intelligence and Statistics, páginas 1273–1282.
Neto, H. N. C., Hribar, J., Dusparic, I., Fernandes, N. C. e Mattos, D. M. (2024). FedSBS: Federated-Learning Participant-Selection Method for Intrusion Detection Systems. Computer Networks, 244:110351.
Owen, S. H. e Daskin, M. S. (1998). Strategic Facility Location: A Review. European Journal of Operational Research, 111(3):423–447.
Patanè, R., Achir, N., Araldo, A. e Boukhatem, L. (2024). Can Vehicular Cloud Replace Edge Computing? Em Wireless Communications and Networking Conference (WCNC). IEEE.
Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G. e Piccialli, F. (2024). Model Aggregation Techniques in Federated Learning: A Comprehensive Survey. Future Generation Computer Systems, 150:272–293.
Su, D. et al. (2024). Communication Cost-Aware Client Selection in Online Federated Learning: A Lyapunov Approach. Computer Networks, página 110517.
Van Der Heijden, R. W., Lukaseder, T. e Kargl, F. (2018). VeReMi: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs. Em Security and Privacy in Communication Networks (SecureComm), páginas 318–337. Springer.
Vinita, L. J. e Vetriselvi, V. (2023). Federated Learning-based Misbehaviour Detection on an Emergency Message Dissemination Scenario for the 6G-enabled Internet of Vehicles. Ad Hoc Networks, 144:103153.
Yakan, H., Fajjari, I., Aitsaadi, N. e Adjih, C. (2023). Federated Learning for V2X Misbehavior Detection System in 5G Edge Networks. Em Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems, páginas 155–163. ACM.
Zhong, Y. et al. (2023). Sybil Attack Detection in VANETs: An LSTM-Based BiGAN Approach. Em Data Security and Privacy Protection (DSPP), páginas 113–120. IEEE.
Zhu, Q. et al. (2021). 3GPP TR 38.901 Channel Model. Em the wiley 5G Ref: the essential 5G reference online, páginas 1–35. Wiley Press Hoboken, NJ, USA.
Boualouache, A. et al. (2023). 5g vehicle-to-everything at the cross-borders: Security challenges and opportunities. Internet of Things Magazine, 6(1):114–119.
Bousalem, B., Sakka, M. A., Silva, V. F., Jaafar, W., Letaifa, A. B. e Langar, R. (2023). DDoS Attacks Mitigation in 5G-V2X Networks: A Reinforcement Learning-Based Approach. Em International Conference on Network and Service Management (CNSM), páginas 1–5. IEEE.
Buyukates, B. e Ulukus, S. (2021). Timely Communication in Federated Learning. Em International Conference on Computer Communications Workshops (INFOCOM WKSHPS), páginas 1–6. IEEE.
Chatzoulis, D. et al. (2023). 5G V2X Performance Comparison for Different Channel Coding Schemes and Propagation Models. Sensors, 23(5):2436.
Committee, S. S. J. S. I. D. et al. (2016). Dedicated Short Range Communications (DSRC) Message set Dictionary. SAE International.
De Souza, L. A. C., Camilo, G. F., Rebello, G. A. F., Guimaraes, L. C., Campista, M. E. M. e Costa, L. H. M. K. (2024). Blockchain-based Approaches for Secure Federated Learning. Em 2024 6th Conference on Blockchain Research & Applications for Innovative Networks and Services (BRAINS), páginas 1–4. IEEE.
de Souza, L. A. C., Camilo, G. F., Rebello, G. A. F., Sammarco, M., Campista, M. E. M. e Costa, L. H. M. (2024). ATHENA-FL: Avoiding Statistical Heterogeneity with One-versus-All in Federated Learning. Journal of Internet Services and Applications, 15(1):273–288.
do Couto Teixeira, D., Almeida, J. M. e Viana, A. C. (2021). On Estimating the Predictability of Human Mobility: The Role of Routine. EPJ Data Science, 10(1):49.
ETSI (2014a). Intelligent Transport Systems (ITS); Vehicular Communications; Basic Set of Applications; Part 2: Specification of Cooperative Awareness Basic Service. ETSI.
ETSI (2014b). Intelligent Transport Systems (ITS); Vehicular Communications; Basic Set of Applications; Part 3: Specifications of Decentralized Environmental Notification Basic Service . ETSI.
Fittipaldi, G., Couto, R. S. e Costa, L. H. (2025). Exploring Traffic Pattern Variability in Vehicular Federated Learning. Computer Communications, página 108279.
Gong, B., Xing, T., Liu, Z., Xi, W. e Chen, X. (2022). Adaptive Client Clustering for Efficient Federated Learning over Non-IID and Imbalanced Data. Transactions on Big Data.
Gonzalez, M. C., Hidalgo, C. A. e Barabasi, A.-L. (2008). Understanding Individual Human Mobility Patterns. Nature, 453(7196):779–782.
Guimaraes, L. C., Rebello, G. A. F., Camilo, G. F., de Souza, L. A. C. e Duarte, O. C. M. (2022). A Threat Monitoring System for Intelligent Data Analytics of Network Traffic. Annals of Telecommunications, 77(7):539–554.
Kamel, J., Wolf, M., Van Der Hei, R. W., Kaiser, A., Urien, P. e Kargl, F. (2020). VeReMi Extension: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs. Em International Conference on Communications (ICC), páginas 1–6. IEEE.
Korba, A. A. et al. (2023). Federated Learning for Zero-Day Attack Detection in 5G and Beyond V2X Networks. Em International Conference on Communications (ICC). IEEE.
Luo, B., Xiao, W., Wang, S., Huang, J. e Tassiulas, L. (2022). Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling. Em Conference on Computer Communications (INFOCOM), páginas 1739–1748. IEEE.
McMahan, B. et al. (2017). Communication-efficient Learning of Deep Networks from Decentralized Data. Artificial Intelligence and Statistics, páginas 1273–1282.
Neto, H. N. C., Hribar, J., Dusparic, I., Fernandes, N. C. e Mattos, D. M. (2024). FedSBS: Federated-Learning Participant-Selection Method for Intrusion Detection Systems. Computer Networks, 244:110351.
Owen, S. H. e Daskin, M. S. (1998). Strategic Facility Location: A Review. European Journal of Operational Research, 111(3):423–447.
Patanè, R., Achir, N., Araldo, A. e Boukhatem, L. (2024). Can Vehicular Cloud Replace Edge Computing? Em Wireless Communications and Networking Conference (WCNC). IEEE.
Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G. e Piccialli, F. (2024). Model Aggregation Techniques in Federated Learning: A Comprehensive Survey. Future Generation Computer Systems, 150:272–293.
Su, D. et al. (2024). Communication Cost-Aware Client Selection in Online Federated Learning: A Lyapunov Approach. Computer Networks, página 110517.
Van Der Heijden, R. W., Lukaseder, T. e Kargl, F. (2018). VeReMi: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs. Em Security and Privacy in Communication Networks (SecureComm), páginas 318–337. Springer.
Vinita, L. J. e Vetriselvi, V. (2023). Federated Learning-based Misbehaviour Detection on an Emergency Message Dissemination Scenario for the 6G-enabled Internet of Vehicles. Ad Hoc Networks, 144:103153.
Yakan, H., Fajjari, I., Aitsaadi, N. e Adjih, C. (2023). Federated Learning for V2X Misbehavior Detection System in 5G Edge Networks. Em Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems, páginas 155–163. ACM.
Zhong, Y. et al. (2023). Sybil Attack Detection in VANETs: An LSTM-Based BiGAN Approach. Em Data Security and Privacy Protection (DSPP), páginas 113–120. IEEE.
Zhu, Q. et al. (2021). 3GPP TR 38.901 Channel Model. Em the wiley 5G Ref: the essential 5G reference online, páginas 1–35. Wiley Press Hoboken, NJ, USA.
Publicado
01/09/2025
Como Citar
SOUZA, Lucas Airam C. de; SAMMARCO, Matteo; ACHIR, Nadjib; CAMPISTA, Miguel Elias M.; COSTA, Luís Henrique M. K..
TOFL: Time Optimized Federated Learning. In: SIMPÓSIO BRASILEIRO DE CIBERSEGURANÇA (SBSEG), 25. , 2025, Foz do Iguaçu/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 871-887.
DOI: https://doi.org/10.5753/sbseg.2025.10576.
