Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203395,
        author = {KUMARAN .V and Saujanya B and Dhayadevi and Pinninti Sai Kumari and Manivannan J},
        title = {Privacy-Preserving Face Recognition System for Smart Campuses Using Federated Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {11922-11931},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203395},
        abstract = {Smart campus environments increasingly rely on face recognition systems for attendance monitoring and access control. However, conventional centralized systems raise serious privacy and security concerns because sensitive biometric data is stored and processed on a central server. To address these challenges, this paper presents a Privacy-Preserving Face Recog- nition System using Federated Learning (FL). The proposed system utilizes the Flower framework and PyTorch to enable distributed model training without sharing raw biometric data among clients. A lightweight GhostFaceNetV2 model is employed for efficient face recognition on edge-compatible devices. The system is trained on the AT&T face dataset across multiple clients using the FedProx optimization algorithm to handle non-IID data distribution. Experimental results demonstrate that the proposed federated model achieves an average evaluation accuracy of approximately 75% while preserving user privacy through local data processing. The architecture also supports low-bandwidth communication and future deployment on resource-constrained devices such as Raspberry Pi.},
        keywords = {Federated Learning, Face Recognition, Smart Campus, Privacy Preservation, GhostFaceNetV2, FedProx, Edge Computing},
        month = {May},
        }