HALO: Uma Abordagem Quântica para Privacidade Diferencial com Robustez Geométrica e Alta Utilidade
Resumo
A integração de Privacidade Diferencial em sistemas de Aprendizado Federado impõe um dilema crítico de utilidade, frequentemente desestabilizando a convergência de arquiteturas clássicas no Cloud-Edge Continuum. Este trabalho introduz o HALO (Hybrid Algorithms Learning on Orbits), uma abordagem fundamentada em Circuitos Quânticos Variacionais que explora a geometria periódica e limitada dos parâmetros quânticos para mitigar o impacto do ruído estocástico. Experimentos comparativos revelam que, no intervalo rigoroso de privacidade (1.0 ≤ ε ≤ 3.0), as redes neurais tradicionais sofrem colapso de predição (∼ 67% de acurácia), enquanto o HALO sustenta estabilidade superior com 98.9% de acurácia. Adicionalmente, a auditoria de risco confirma a eficácia da proteção contra ataques de inferência de membros (MIA < 0.60). Os resultados validam a robustez geométrica quântica como uma alternativa superior para conciliar alto desempenho preditivo e garantias formais de privacidade em ambientes distribuídos.Referências
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., and Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pages 308–318. ACM.
Alpaydin, E. and Kaynak, C. Optical recognition of handwritten digits data set. uci machine learning repository (1998). URL [link].
Biamonte, J. (2021). Universal variational quantum computation. Physical Review A, 103(3):L030401.
Bishop, C. M. and Nasrabadi, N. M. (2006). Pattern recognition and machine learning, volume 4. Springer.
Du, Y., Hsieh, M.-H., Liu, T., and Tao, D. (2021). Quantum noise protects quantum classifiers against adversarial attacks. Physical Review Research, 3(2):023153.
Dwork, C., McSherry, F., Nissim, K., and Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In Theory of cryptography conference, pages 265–284. Springer.
Freire, M., Mello, T. L., Sant’Anna, I., Maia, A., Moreira, R., Rivelino, R., and Peixoto, M. (2025). Rana: Uma abordagem híbrida para qkd bb84 com expansão e encapsulamento de chave. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), pages 938–951. SBC.
Gholipour, H., Bozorgnia, F., Hambarde, K., Mohammadigheymasi, H., Mancilla, J., Sequeira, A., Neves, J., Proença, H., and Challenger, M. (2025). A laplacian-based quantum graph neural networks for quantum semi-supervised learning. Quantum Information Processing, 24(4):106.
Gkonis, P. K., Trakadas, P., Karkazis, P., and Leligou, H. C. (2023). A survey on iot-edge-cloud continuum systems: Status, challenges, use cases, and open issues. Future Internet, 15(12):383.
Ilonen, J., Kamarainen, J.-K., and Lampinen, J. (2003). Differential evolution training algorithm for feed-forward neural networks. Neural Processing Letters, 17(1):93–105.
Kandala, A., Mezzacapo, A., Temme, K., Takita, M., Brink, M., Chow, J. M., and Gambetta, J. M. (2017). Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets. Nature, 549(7671):242–246.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553):436–444.
Li, W., Lu, S., and Deng, D.-L. (2021). Quantum federated learning through blind quantum computing. Science China Physics, Mechanics & Astronomy, 64(10):100312.
Maia, A., Freire, M., Mello, T., Rodrigues-Filho, R., Almeida, E., Prazeres, C., Figueiredo, G., and Peixoto, M. (2025). Q-edge: Leveraging quantum computing for enhanced software engineering in vehicular networks. In Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, pages 1457–1467.
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR.
Mitarai, K., Negoro, M., Kitagawa, M., and Fujii, K. (2018). Quantum circuit learning. Physical Review A, 98(3):032309.
Nasr, M., Shokri, R., and Houmansadr, A. (2019). Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In 2019 IEEE Symposium on Security and Privacy (SP), pages 739–753. IEEE.
Peixoto, M. L. M. (2024). Quantum edge computing for data analysis in connected autonomous vehicles. In 2024 IEEE Symposium on Computers and Communications (ISCC), pages 1–6. IEEE.
Ponomareva, N., Hazimeh, H., Kurakin, A., Xu, Z., Denison, C., McMahan, H. B., Vassilvitskii, S., Chien, S., and Thakurta, A. G. (2023). How to dp-fy ml: A practical guide to machine learning with differential privacy. Journal of Artificial Intelligence Research, 77:1113–1201.
Schuld, M., Sweke, R., and Meyer, J. J. (2021). Effect of data encoding on the expressive power of variational quantum-machine-learning models. Physical Review A, 103(3):032430.
Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017). Membership inference attacks against machine learning models. In 2017 IEEE Symposium on Security and Privacy (SP), pages 3–18. IEEE.
Yu, S., Zhu, K., Liang, F., Wang, J., Kant, K., and Yin, L. (2026). Robust multimodal federated learning for non-iid multimodal data with incompleteness. Future Generation Computer Systems, 174:107948.
Alpaydin, E. and Kaynak, C. Optical recognition of handwritten digits data set. uci machine learning repository (1998). URL [link].
Biamonte, J. (2021). Universal variational quantum computation. Physical Review A, 103(3):L030401.
Bishop, C. M. and Nasrabadi, N. M. (2006). Pattern recognition and machine learning, volume 4. Springer.
Du, Y., Hsieh, M.-H., Liu, T., and Tao, D. (2021). Quantum noise protects quantum classifiers against adversarial attacks. Physical Review Research, 3(2):023153.
Dwork, C., McSherry, F., Nissim, K., and Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In Theory of cryptography conference, pages 265–284. Springer.
Freire, M., Mello, T. L., Sant’Anna, I., Maia, A., Moreira, R., Rivelino, R., and Peixoto, M. (2025). Rana: Uma abordagem híbrida para qkd bb84 com expansão e encapsulamento de chave. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), pages 938–951. SBC.
Gholipour, H., Bozorgnia, F., Hambarde, K., Mohammadigheymasi, H., Mancilla, J., Sequeira, A., Neves, J., Proença, H., and Challenger, M. (2025). A laplacian-based quantum graph neural networks for quantum semi-supervised learning. Quantum Information Processing, 24(4):106.
Gkonis, P. K., Trakadas, P., Karkazis, P., and Leligou, H. C. (2023). A survey on iot-edge-cloud continuum systems: Status, challenges, use cases, and open issues. Future Internet, 15(12):383.
Ilonen, J., Kamarainen, J.-K., and Lampinen, J. (2003). Differential evolution training algorithm for feed-forward neural networks. Neural Processing Letters, 17(1):93–105.
Kandala, A., Mezzacapo, A., Temme, K., Takita, M., Brink, M., Chow, J. M., and Gambetta, J. M. (2017). Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets. Nature, 549(7671):242–246.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553):436–444.
Li, W., Lu, S., and Deng, D.-L. (2021). Quantum federated learning through blind quantum computing. Science China Physics, Mechanics & Astronomy, 64(10):100312.
Maia, A., Freire, M., Mello, T., Rodrigues-Filho, R., Almeida, E., Prazeres, C., Figueiredo, G., and Peixoto, M. (2025). Q-edge: Leveraging quantum computing for enhanced software engineering in vehicular networks. In Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, pages 1457–1467.
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR.
Mitarai, K., Negoro, M., Kitagawa, M., and Fujii, K. (2018). Quantum circuit learning. Physical Review A, 98(3):032309.
Nasr, M., Shokri, R., and Houmansadr, A. (2019). Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In 2019 IEEE Symposium on Security and Privacy (SP), pages 739–753. IEEE.
Peixoto, M. L. M. (2024). Quantum edge computing for data analysis in connected autonomous vehicles. In 2024 IEEE Symposium on Computers and Communications (ISCC), pages 1–6. IEEE.
Ponomareva, N., Hazimeh, H., Kurakin, A., Xu, Z., Denison, C., McMahan, H. B., Vassilvitskii, S., Chien, S., and Thakurta, A. G. (2023). How to dp-fy ml: A practical guide to machine learning with differential privacy. Journal of Artificial Intelligence Research, 77:1113–1201.
Schuld, M., Sweke, R., and Meyer, J. J. (2021). Effect of data encoding on the expressive power of variational quantum-machine-learning models. Physical Review A, 103(3):032430.
Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017). Membership inference attacks against machine learning models. In 2017 IEEE Symposium on Security and Privacy (SP), pages 3–18. IEEE.
Yu, S., Zhu, K., Liang, F., Wang, J., Kant, K., and Yin, L. (2026). Robust multimodal federated learning for non-iid multimodal data with incompleteness. Future Generation Computer Systems, 174:107948.
Publicado
25/05/2026
Como Citar
MAIA, Adriano et al.
HALO: Uma Abordagem Quântica para Privacidade Diferencial com Robustez Geométrica e Alta Utilidade. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 44. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 828-841.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2026.19640.
