ORIGINAL RESEARCH article
Front. Big Data
Sec. Cybersecurity and Privacy
Federated Learning for Teacher Data Privacy Protection: A Study in the Context of the PIPL
Provisionally accepted
- Baoji University of Arts and Sciences, Xi'an, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Taking the Personal Information Protection Law (PIPL) as a starting point, this study focuses on the application of Federated Learning (FL) in protecting teacher data privacy, analyzing the compliance challenges it faces, and proposing corresponding strategies. By combining quantitative and qualitative analysis, the study first examines the limitations of traditional centralized machine learning methods in privacy protection and highlights the advantages of FL in terms of data decentralization and privacy preservation. Particular attention is given to how techniques such as Differential Privacy serve as the primary empirically validated privacy mechanism, while other privacy-enhancing technologies, including Secure Multi-Party Computation (SMC), are discussed at a theoretical and compliance-analytical level to contextualize FL frameworks within the requirements of the PIPL. The findings indicate that, under simulated experimental conditions, FL can conceptually contribute to reducing the risk of data breaches and supporting principle-level alignment with the PIPL through measures such as data anonymization, minimization, and encrypted transmission. Finally, based on the research outcomes, a compliance framework tailored for protecting teacher data privacy is proposed, providing theoretical foundations and practical recommendations for the implementation of relevant technologies.
Keywords: Compliance, Differential privacy, Federated learning, PersonalInformation Protection Law, Teacher Data Protection
Received: 08 Aug 2025; Accepted: 19 Jan 2026.
Copyright: © 2026 Chen, Qi, Han, Fan and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xiu Zhi Qi
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.