Preservando a Utilidade de Dados Urbanos via Alocação Adaptativa de Ruído em Privacidade Diferencial
Resumo
No cenário das cidades inteligentes, os sistemas distribuídos demandam mecanismos de preservação de privacidade que equilibrem utilidade dos dados e eficiência computacional. Abordagens tradicionais degradam o desempenho de aprendizado de máquina ao aplicar ruído uniforme sobre todas as características. Este trabalho apresenta o Adaptive Differential Privacy via Mutual Information (APDIM), uma estratégia adaptativa que aloca ruído conforme a relevância das características e preserva dependências estatísticas por meio de perturbação sensível à correlação. Os resultados mostram que o APDIM mantém elevada acurácia com baixo custo computacional, sendo adequado a ambientes distribuídos com recursos limitados.Referências
Aminifar, A., Shaban-Nejad, A., Lavigne, M., and Moghaddam, S. (2022). Extremely randomized trees with privacy preservation for distributed structured health data. IEEE Journal of Biomedical and Health Informatics, 26(7):3311–3322.
Chen, Q., Ni, Z., Zhu, X., Lyu, M., Liu, W., and Xia, P. (2024a). Dynamic edge-based high-dimensional data aggregation with differential privacy. Electronics, 13(16):3346.
Chen, Z., Zheng, H., and Liu, G. (2024b). Awdp-fl: An adaptive differential privacy federated learning framework. Electronics, 13(19):3959.
Coelho, R., Almeida, B., and Costa, D. (2024). A new k-anonymity method based on generalization first k-member clustering for healthcare data. Journal of Biomedical Informatics, 149:104579.
Dwork, C., Roth, A., et al. (2014). The algorithmic foundations of differential privacy. Foundations and trends® in theoretical computer science, 9(3–4):211–407.
Fernandes, N., McIver, A., and Morgan, C. (2021). The laplace mechanism has optimal utility for differential privacy over continuous queries. In 2021 36th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS), pages 1–12.
Hall, M. A. (1999). Correlation-based feature selection for machine learning. PhD thesis, The University of Waikato.
Mao, Y., Chen, X., Zhang, Y., Li, J., and Liu, Y. (2018). A privacy-preserving deep learning approach for face recognition with edge computing. In Proceedings of the 2018 USENIX Workshop on Hot Topics in Edge Computing (HotEdge). USENIX Association.
Pimenta, I., Silva, D., Moura, E., Silveira, M., and Gomes, R. L. (2024). Impact of data anonymization in machine learning models. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, pages 188–191.
Pimenta, I. A., Araújo, R. S., Rodrigues, R. L., Silveira, M. M., and Gomes, R. L. (2025). Anonimização de dados para inteligência artificial usando o algoritmo da tropa dos gorilas. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), pages 448–461. SBC.
Silveira, M. M., Portela, A. L., Menezes, R. A., Souza, M. S., Silva, D. S., Mesquita, M. C., and Gomes, R. L. (2023). Data protection based on searchable encryption and anonymization techniques. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, pages 1–5. IEEE.
Souza, M. S., Ribeiro, S. E. S. B., Lima, V. C., Cardoso, F. J., and Gomes, R. L. (2024). Combining regular expressions and machine learning for sql injection detection in urban computing. Journal of Internet Services and Applications, 15(1):103–111.
Wang, Y., Yang, C., Lan, S., Zhu, L., and Zhang, Y. (2024). End-edge-cloud collaborative computing for deep learning: A comprehensive survey. IEEE Communications Surveys & Tutorials, 26(4):2647–2683.
Yang, B., Sato, I., and Nakagawa, H. (2015). Bayesian differential privacy on correlated data. In Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, SIGMOD ’15, pages 747–762, Melbourne, Australia. ACM.
Yang, W., Liew, Z. Q., Lim, W. Y. B., Xiong, Z., Niyato, D., Chi, X., Cao, X., and Letaief, K. B. (2022). Semantic communication meets edge intelligence. IEEE wireless communications, 29(5):28–35.
Yao, A., Li, G., Li, X., Jiang, F., Xu, J., and Liu, X. (2023). Differential privacy in edge computing-based smart city applications: Security issues, solutions and future directions. Array, 19:100293.
Zhang, X., Yang, F., Guo, Y., Yu, H., Wang, Z., and Zhang, Q. (2023). Adaptive differential privacy mechanism based on entropy theory for preserving deep neural networks. Mathematics, 11(2):330.
Chen, Q., Ni, Z., Zhu, X., Lyu, M., Liu, W., and Xia, P. (2024a). Dynamic edge-based high-dimensional data aggregation with differential privacy. Electronics, 13(16):3346.
Chen, Z., Zheng, H., and Liu, G. (2024b). Awdp-fl: An adaptive differential privacy federated learning framework. Electronics, 13(19):3959.
Coelho, R., Almeida, B., and Costa, D. (2024). A new k-anonymity method based on generalization first k-member clustering for healthcare data. Journal of Biomedical Informatics, 149:104579.
Dwork, C., Roth, A., et al. (2014). The algorithmic foundations of differential privacy. Foundations and trends® in theoretical computer science, 9(3–4):211–407.
Fernandes, N., McIver, A., and Morgan, C. (2021). The laplace mechanism has optimal utility for differential privacy over continuous queries. In 2021 36th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS), pages 1–12.
Hall, M. A. (1999). Correlation-based feature selection for machine learning. PhD thesis, The University of Waikato.
Mao, Y., Chen, X., Zhang, Y., Li, J., and Liu, Y. (2018). A privacy-preserving deep learning approach for face recognition with edge computing. In Proceedings of the 2018 USENIX Workshop on Hot Topics in Edge Computing (HotEdge). USENIX Association.
Pimenta, I., Silva, D., Moura, E., Silveira, M., and Gomes, R. L. (2024). Impact of data anonymization in machine learning models. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, pages 188–191.
Pimenta, I. A., Araújo, R. S., Rodrigues, R. L., Silveira, M. M., and Gomes, R. L. (2025). Anonimização de dados para inteligência artificial usando o algoritmo da tropa dos gorilas. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), pages 448–461. SBC.
Silveira, M. M., Portela, A. L., Menezes, R. A., Souza, M. S., Silva, D. S., Mesquita, M. C., and Gomes, R. L. (2023). Data protection based on searchable encryption and anonymization techniques. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, pages 1–5. IEEE.
Souza, M. S., Ribeiro, S. E. S. B., Lima, V. C., Cardoso, F. J., and Gomes, R. L. (2024). Combining regular expressions and machine learning for sql injection detection in urban computing. Journal of Internet Services and Applications, 15(1):103–111.
Wang, Y., Yang, C., Lan, S., Zhu, L., and Zhang, Y. (2024). End-edge-cloud collaborative computing for deep learning: A comprehensive survey. IEEE Communications Surveys & Tutorials, 26(4):2647–2683.
Yang, B., Sato, I., and Nakagawa, H. (2015). Bayesian differential privacy on correlated data. In Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, SIGMOD ’15, pages 747–762, Melbourne, Australia. ACM.
Yang, W., Liew, Z. Q., Lim, W. Y. B., Xiong, Z., Niyato, D., Chi, X., Cao, X., and Letaief, K. B. (2022). Semantic communication meets edge intelligence. IEEE wireless communications, 29(5):28–35.
Yao, A., Li, G., Li, X., Jiang, F., Xu, J., and Liu, X. (2023). Differential privacy in edge computing-based smart city applications: Security issues, solutions and future directions. Array, 19:100293.
Zhang, X., Yang, F., Guo, Y., Yu, H., Wang, Z., and Zhang, Q. (2023). Adaptive differential privacy mechanism based on entropy theory for preserving deep neural networks. Mathematics, 11(2):330.
Publicado
25/05/2026
Como Citar
PIMENTA, Ivo A.; LEE, Marcelo H.; MOURA, Evellin S.; NASCIMENTO, Erick S.; R. FILHO, Geraldo; GOMES, Rafael L..
Preservando a Utilidade de Dados Urbanos via Alocação Adaptativa de Ruído em Privacidade Diferencial. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 10. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 239-252.
ISSN 2595-2706.
DOI: https://doi.org/10.5753/courb.2026.23089.
