EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Privacy-Preserving MLOps with Differential Privacy and AI-Guided Tuning

Chhaya, Jay Nankani, Rohit Gupta, Atul Khanna

International Journal of Global Innovations and Solutions · 2026

DOI: 10.63412/ezdfsg07 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Global Innovations and Solutions, 2026. Verfasst von Chhaya und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

When machine learning systems transition from being deployed within research environments to enterprise-scale deployment pipelines, protecting data privacy poses an increasing challenge while the model is being trained and/or used. Privacy-preserving techniques will predominantly rely on some form of static differential privacy (DP) constraint, with the challenge often being to balance privacy requirements with model performance, particularly with dynamic workloads. In this paper, we propose a new Privacy-Preserving MLOps (PP-MLOps) framework that combines AI-aided adaptive tuning of differential privacy in the automated MLOps lifecycle. These proposed agent approaches allow for a flexible way to continuously assess privacy risks, regulatory obligations to privacy and confidentiality, and the value of model utility metrics while adapting DP scale of noise, depth of clipping, and privacy budgets (ε, δ) in real-time to achieve optimal model utility. The continuous optimization of DP in CI/CD pipeline operations is actualized through also using reinforcement-learning based controllers to adjust for a range of privacy and performance tradeoff situations in real-time. Evaluation simulations show a 20% improvement in model accuracy retention in regulation compliant DP tuning and operational measures against traditional fixed DP configurations of varying distributions and operational risks. This study can lay the foundation for fully autonomous risk sensing and regulatory compliant MLOps while translating theoretical claims of privacy, application and assurance in a pragmatic framework machine learning deployment at scale.

Zitieren

APA

Chhaya, Nankani, J., Gupta, R., & Khanna, A. (2026). Privacy-Preserving MLOps with Differential Privacy and AI-Guided Tuning. International Journal of Global Innovations and Solutions. https://doi.org/10.63412/ezdfsg07

Vancouver

Chhaya, Nankani J, Gupta R, Khanna A. Privacy-Preserving MLOps with Differential Privacy and AI-Guided Tuning. International Journal of Global Innovations and Solutions. 2026. doi:10.63412/ezdfsg07

BibTeX
@article{Chhaya2026,
  author = {Chhaya and Nankani, Jay and Gupta, Rohit and Khanna, Atul},
  title = {Privacy-Preserving MLOps with Differential Privacy and AI-Guided Tuning},
  journal = {International Journal of Global Innovations and Solutions},
  year = {2026},
  doi = {10.63412/ezdfsg07}
}
Kostenlos starten →