Ingeniería de software aplicada al aprendizaje federado: estudio de bibliotecas y mecanismos de protección de datos
DOI:
https://doi.org/10.63688/cognitivatech.v2.i1.30Keywords:
aprendizaje federado, privacidad de datos, sistemas distribuidos, ingeniería de software.Abstract
El federated learning (FL) se ha consolidado como una alternativa innovadora dentro del aprendizaje automático distribuido, permitiendo entrenar modelos sin necesidad de centralizar los datos, lo que favorece la privacidad y el cumplimiento de regulaciones de protección de información. Sin embargo, a pesar de sus ventajas, su adopción práctica sigue siendo limitada debido a desafíos técnicos, especialmente en lo relacionado con la seguridad, la privacidad y la complejidad de implementación en entornos reales. Este estudio analiza bibliotecas de FL desde una perspectiva de ingeniería de software, evaluando cómo implementan componentes esenciales como el entrenamiento local, la agregación de modelos, la comunicación entre clientes y servidores, y los mecanismos de protección de datos. Además, se examina el soporte para funcionalidades avanzadas como auditoría, detección de anomalías y verificación de privacidad. La metodología utilizada se basa en una revisión estructurada de la literatura y un análisis comparativo de diez bibliotecas seleccionadas por su relevancia en la comunidad académica y de desarrollo. Los resultados evidencian que, aunque todas las bibliotecas soportan las operaciones básicas del FL, existen diferencias significativas en su arquitectura, extensibilidad y nivel de madurez. Asimismo, se identifica una brecha importante en la integración de mecanismos avanzados de seguridad, los cuales suelen requerir extensiones adicionales. Se concluye que el principal reto del FL no es únicamente algorítmico, sino también de ingeniería de software, ya que se requiere equilibrar privacidad, utilidad del modelo y eficiencia computacional. Esto resalta la necesidad de desarrollar frameworks más robustos, flexibles y seguros para su adopción en aplicaciones reales.References
AbdulRahman, S., Tout, H., Ould-Slimane, H., Mourad, A., Talhi, C., & Guizani, M. (2020). A survey on federated learning: The journey from centralized to distributed on-site learning and beyond. IEEE Internet of Things Journal. https://scholar.google.com/scholar?q=A+survey+on+federated+learning+The+journey+from+centralized+to+distributed+on-site+learning+and+beyond DOI: https://doi.org/10.1109/JIOT.2020.3030072
Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020). Federated learning: A survey on enabling technologies, protocols, and applications. IEEE Access. https://scholar.google.com/scholar?q=Federated+learning+a+survey+on+enabling+technologies+protocols+and+applications+Aledhari DOI: https://doi.org/10.1109/ACCESS.2020.3013541
Balasubramanian, K., & Mala, K. (2018). Zero knowledge proofs: A survey. IGI Global. https://scholar.google.com/scholar?q=Zero+knowledge+proofs+a+survey+Balasubramanian+Mala+2018 DOI: https://doi.org/10.4018/978-1-5225-2915-6.ch009
Chai, D., Wang, L., Yang, L., et al. (2024). A survey for federated learning evaluations: Goals and measures. IEEE Transactions on Knowledge and Data Engineering. https://scholar.google.com/scholar?q=A+survey+for+federated+learning+evaluations+goals+and+measures+Chai+2024 DOI: https://doi.org/10.1109/TKDE.2024.3382002
El Ouadrhiri, A., & Abdelhadi, A. (2022). Differential privacy for deep and federated learning: A survey. IEEE Access. https://scholar.google.com/scholar?q=Differential+privacy+for+deep+and+federated+learning+A+survey DOI: https://doi.org/10.1109/ACCESS.2022.3151670
Kairouz, P., et al. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning. https://scholar.google.com/scholar?q=Advances+and+open+problems+in+federated+learning+Kairouz DOI: https://doi.org/10.1561/2200000083
Lim, W. Y. B., et al. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials. https://scholar.google.com/scholar?q=Federated+learning+in+mobile+edge+networks+a+comprehensive+survey+Lim DOI: https://doi.org/10.1109/COMST.2020.2986024
Liu, J., Huang, J., Zhou, Y., Li, X., Ji, S., Xiong, H., & Dou, D. (2022). From distributed machine learning to federated learning: A survey. Knowledge and Information Systems. https://scholar.google.com/scholar?q=From+distributed+machine+learning+to+federated+learning+A+survey+Liu+2022 DOI: https://doi.org/10.1007/s10115-022-01664-x
Lyu, L., Yu, H., & Yang, Q. (2020). Threats to federated learning: A survey. arXiv. https://scholar.google.com/scholar?q=Threats+to+federated+learning+a+survey+Lyu+2020 DOI: https://doi.org/10.1007/978-3-030-63076-8_1
Nguyen, D. C., et al. (2021). Federated learning for Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials. https://scholar.google.com/scholar?q=Federated+learning+for+Internet+of+Things+A+comprehensive+survey+Nguyen+2021 DOI: https://doi.org/10.1109/COMST.2021.3075439
Nguyen, D. C., et al. (2022). Federated learning for smart healthcare: A survey. ACM Computing Surveys. https://scholar.google.com/scholar?q=Federated+learning+for+smart+healthcare+a+survey+Nguyen+2022 DOI: https://doi.org/10.1145/3501296
Quan, M. K., et al. (2025). Federated learning for cyber physical systems: A comprehensive survey. https://scholar.google.com/scholar?q=Federated+learning+for+cyber+physical+systems+a+comprehensive+survey+Quan+2025
Sánchez, P. M. S., et al. (2024). Federatedtrust: A solution for trustworthy federated learning. Future Generation Computer Systems. https://scholar.google.com/scholar?q=Federatedtrust+a+solution+for+trustworthy+federated+learning+2024 DOI: https://doi.org/10.1016/j.future.2023.10.013
Wang, Y., Su, Z., Zhang, N., & Benslimane, A. (2021). Learning in the air: Secure federated learning for UAV-assisted crowdsensing. IEEE Transactions on Network Science and Engineering. https://scholar.google.com/scholar?q=Learning+in+the+Air+Secure+Federated+Learning+for+UAV-Assisted+Crowdsensing DOI: https://doi.org/10.1109/TNSE.2020.3014385
Wen, J., Zhang, Z., Lan, Y., Cui, Z., Cai, J., & Zhang, W. (2023). A survey on federated learning: Challenges and applications. International Journal of Machine Learning and Cybernetics. https://scholar.google.com/scholar?q=A+survey+on+federated+learning+Challenges+and+applications+Wen+2023 DOI: https://doi.org/10.1007/s13042-022-01647-y
Xia, Q., Ye, W., Tao, Z., Wu, J., & Li, Q. (2021). A survey of federated learning for edge computing. High-Confidence Computing. https://scholar.google.com/scholar?q=A+survey+of+federated+learning+for+edge+computing+Xia+Ye+2021 DOI: https://doi.org/10.1016/j.hcc.2021.100008
Ye, M., Shen, W., Du, B., et al. (2025). Vertical federated learning for effectiveness, security, applicability: A survey. ACM Computing Surveys. https://scholar.google.com/scholar?q=Vertical+federated+learning+for+effectiveness+security+applicability+a+survey DOI: https://doi.org/10.1145/3720539
Yin, X., Zhu, Y., & Hu, J. (2021). Privacy-preserving federated learning: A taxonomy and survey. ACM Computing Surveys. https://scholar.google.com/scholar?q=Privacy-preserving+federated+learning+a+taxonomy+survey+Yin+2021
Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., & Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems. https://scholar.google.com/scholar?q=A+survey+on+federated+learning+Zhang+2021+Knowledge-Based+Systems DOI: https://doi.org/10.1016/j.knosys.2021.106775
Published
Issue
Section
License
Copyright (c) 2025 Gustavo Adolfo Hernández Rosado (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
