A Comprehensive Review of Privacy-Preserving Techniques in Artificial Intelligence and Machine Learning: Challenges, Solutions, and Future Directions

Hayder Majid  Sachit

Authors

Hayder Majid Sachit University of Wasit, College of Science, Iraq

Keywords:

Privacy-Preserving, Artificial Intelligence (AI), Machine Learning (ML), Federated Learning, Differential Privacy

Abstract

Fast progress of new technologies like Artificial Intelligence (AI) and Machine Learning (ML) is bringing forth important issues when it comes to data privacy in different fields. AI and ML solutions depend on great volumes of data that frequently include personal or organizational data, some of which is sensitive. Preserving privacy with no degradation of model performance presents major technical, ethical and legal issues. This survey presents an extensive overview of the most widely adopted privacy-preserving methodologies in AI and ML, including encryption based techniques, federated learning, differential privacy, data anonymization, blockchain-inspired approaches as well as private AI APIs and synthetic data. 875 Each approach is evaluated by its respective advantage, disadvantage and applicable conditions. Moreover, a comparison shows trade-offs between security level, performance and scalability and hybrid solutions are found most promising for practical use cases. Finally, the paper concludes by providing a few research directions, in particular highlighting the mandatory support for adaptive privacy preservation measures, scalable solutions and consistent global legislations. This is a thorough reference text for those who wish to design secure, performant and privacy-focused AI and ML systems.

References

E. N. Kucur, T. Buyuktanir, M. Ugurelli, and K. Yildiz, “Privacy-Preserving Machine Learning Techniques: Cryptographic Approaches, Challenges, and Future Directions,” Appl. Sci., vol. 16, no. 1, p. 277, 2025.

R. N. SABER and Y. H. MASEEH, “Privacy-preserving machine learning: a review of federated learning techniques and‎ applications,” Int. J., vol. 11, no. 1, pp. 30–39, 2025, doi: https://doi.org/10.14419/af03y111.

J. Lu, “Survey on Privacy-Preserving Techniques for Federated Learning”.

H. Schwarz, “Comprehensive review on privacy-preserving machine learning techniques for exploring federated learning,” Eur. J. Intell. Autom. Res., vol. 3, no. 2, 2024.

E. V. Svanovich, A. T., & Petrova, “Privacy Preserving AI: Federated Learning and Differential Privacy,” AI Sci. Acad. J..

A. M. Akinsiku, “A comprehensive survey of federated learning approaches for privacy-preserving machine learning,” Tech-sph. J. Pure Appl. Sci., vol. 2, no. 1, 2025.

E. Shalabi, W. Khedr, E. Rushdy, and A. Salah, “A comparative study of privacy-preserving techniques in federated learning: A performance and security analysis,” Information, vol. 16, no. 3, p. 244, 2025.

E.D.Kanmani Ruby, “Advanced Privacy-Preserving Federated Learning in 6G Networks Using Differential Privacy and Homomorphic Encryption,” Int. J. Intell. Syst. Appl. Eng., vol. 12, no. 23s SE-Research Article, pp. 1–7, Aug. 2024, [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/6427

S. Barański, “A Survey on Privacy-Preserving Machine Learning Inference,” TASK Q., vol. 28, no. 2, 2024.

W. Jin et al., “FedML-HE: An efficient homomorphic-encryption-based privacy-preserving federated learning system,” arXiv Prepr. arXiv2303.10837, 2023.

T. H. Rafi, F. A. Noor, T. Hussain, and D.-K. Chae, “Fairness and privacy preserving in federated learning: A survey,” Inf. Fusion, vol. 105, p. 102198, 2024.

V. S. Naresh, A. Venkata Raju, and O. Srinivasa Rao, “Secure Multiparty Computation for Privacy‐Preserving Machine Learning in Healthcare: A Comprehensive Survey,” Wiley Interdiscip. Rev. Comput. Stat., vol. 17, no. 3, p. e70046, 2025.

C. Dwork, “Differential privacy: A survey of results,” in International conference on theory and applications of models of computation, Springer, 2008, pp. 1–19.

F. Liu, Z. Zheng, Y. Shi, Y. Tong, and Y. Zhang, “A survey on federated learning: a perspective from multi-party computation,” Front. Comput. Sci., vol. 18, no. 1, p. 181336, 2024.

C. Dwork, “Differential privacy: A survey of results,” in Proc. Int. Conf. Theory and Applications of Models of Computation (TAMC). Berlin, Germany: Springer, 2008, pp. 1–19.