FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments

The widespread deployment of CCTV systems has significantly enhanced surveillance and public safety across various environments. However, the emergence of deepfake technology poses serious challenges by enabling malicious manipulation of video footage, compromising the reliability of CCTV systems fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Jimin Ha, Abir El Azzaoui, Jong Hyuk Park
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/788
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199739846361088
author Jimin Ha
Abir El Azzaoui
Jong Hyuk Park
author_facet Jimin Ha
Abir El Azzaoui
Jong Hyuk Park
author_sort Jimin Ha
collection DOAJ
description The widespread deployment of CCTV systems has significantly enhanced surveillance and public safety across various environments. However, the emergence of deepfake technology poses serious challenges by enabling malicious manipulation of video footage, compromising the reliability of CCTV systems for evidence collection and privacy protection. Existing deepfake detection solutions often suffer from high computational overhead and are unsuitable for real-time deployment on resource-constrained CCTV cameras. This paper proposes FL-TENB4, a Federated-Learning-enhanced Tiny EfficientNetB4-Lite framework for deepfake detection in CCTV environments. The proposed architecture integrates Tiny Machine Learning (TinyML) techniques with EfficientNetB4-Lite, a lightweight convolutional neural network optimized for edge devices, and employs a Federated Learning (FL) approach for collaborative model updates. The TinyML-based local model ensures real-time deepfake detection with minimal latency, while FL enables privacy-preserving training by aggregating model updates without transferring sensitive video data to centralized servers. The effectiveness of the proposed system is validated using the FaceForensics++ dataset under resource-constrained conditions. Experimental results demonstrate that FL-TENB4 achieves high detection accuracy, reduced model size, and low inference latency, making it highly suitable for real-world CCTV environments.
format Article
id doaj-art-75fd86b80e804f79921c0c4e7d94e28f
institution OA Journals
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-75fd86b80e804f79921c0c4e7d94e28f2025-08-20T02:12:33ZengMDPI AGSensors1424-82202025-01-0125378810.3390/s25030788FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV EnvironmentsJimin Ha0Abir El Azzaoui1Jong Hyuk Park2Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaThe widespread deployment of CCTV systems has significantly enhanced surveillance and public safety across various environments. However, the emergence of deepfake technology poses serious challenges by enabling malicious manipulation of video footage, compromising the reliability of CCTV systems for evidence collection and privacy protection. Existing deepfake detection solutions often suffer from high computational overhead and are unsuitable for real-time deployment on resource-constrained CCTV cameras. This paper proposes FL-TENB4, a Federated-Learning-enhanced Tiny EfficientNetB4-Lite framework for deepfake detection in CCTV environments. The proposed architecture integrates Tiny Machine Learning (TinyML) techniques with EfficientNetB4-Lite, a lightweight convolutional neural network optimized for edge devices, and employs a Federated Learning (FL) approach for collaborative model updates. The TinyML-based local model ensures real-time deepfake detection with minimal latency, while FL enables privacy-preserving training by aggregating model updates without transferring sensitive video data to centralized servers. The effectiveness of the proposed system is validated using the FaceForensics++ dataset under resource-constrained conditions. Experimental results demonstrate that FL-TENB4 achieves high detection accuracy, reduced model size, and low inference latency, making it highly suitable for real-world CCTV environments.https://www.mdpi.com/1424-8220/25/3/788Federated LearningTinyMLEfficientNetB4deepfake detectionCCTV environment
spellingShingle Jimin Ha
Abir El Azzaoui
Jong Hyuk Park
FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
Sensors
Federated Learning
TinyML
EfficientNetB4
deepfake detection
CCTV environment
title FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
title_full FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
title_fullStr FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
title_full_unstemmed FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
title_short FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments
title_sort fl tenb4 a federated learning enhanced tiny efficientnetb4 lite approach for deepfake detection in cctv environments
topic Federated Learning
TinyML
EfficientNetB4
deepfake detection
CCTV environment
url https://www.mdpi.com/1424-8220/25/3/788
work_keys_str_mv AT jiminha fltenb4afederatedlearningenhancedtinyefficientnetb4liteapproachfordeepfakedetectionincctvenvironments
AT abirelazzaoui fltenb4afederatedlearningenhancedtinyefficientnetb4liteapproachfordeepfakedetectionincctvenvironments
AT jonghyukpark fltenb4afederatedlearningenhancedtinyefficientnetb4liteapproachfordeepfakedetectionincctvenvironments