Lightweight Deepfake Detection Based on Multi-Feature Fusion

Deepfake technology utilizes deep learning (DL)-based face manipulation techniques to seamlessly replace faces in videos, creating highly realistic but artificially generated content. Although this technology has beneficial applications in media and entertainment, misuse of its capabilities may lead...

Full description

Saved in:
Bibliographic Details
Main Authors: Siddiqui Muhammad Yasir, Hyun Kim
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/4/1954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080570381434880
author Siddiqui Muhammad Yasir
Hyun Kim
author_facet Siddiqui Muhammad Yasir
Hyun Kim
author_sort Siddiqui Muhammad Yasir
collection DOAJ
description Deepfake technology utilizes deep learning (DL)-based face manipulation techniques to seamlessly replace faces in videos, creating highly realistic but artificially generated content. Although this technology has beneficial applications in media and entertainment, misuse of its capabilities may lead to serious risks, including identity theft, cyberbullying, and false information. The integration of DL with visual cognition has resulted in important technological improvements, particularly in addressing privacy risks caused by artificially generated “deepfake” images on digital media platforms. In this study, we propose an efficient and lightweight method for detecting deepfake images and videos, making it suitable for devices with limited computational resources. In order to reduce the computational burden usually associated with DL models, our method integrates machine learning classifiers in combination with keyframing approaches and texture analysis. Moreover, the features extracted with a histogram of oriented gradients (HOG), local binary pattern (LBP), and KAZE bands were integrated to evaluate using random forest, extreme gradient boosting, extra trees, and support vector classifier algorithms. Our findings show a feature-level fusion of HOG, LBP, and KAZE features improves accuracy to 92% and 96% on FaceForensics++ and Celeb-DF(v2), respectively.
format Article
id doaj-art-dc82b85604fe40c59e60114278fb6a3e
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-dc82b85604fe40c59e60114278fb6a3e2025-08-20T02:44:55ZengMDPI AGApplied Sciences2076-34172025-02-01154195410.3390/app15041954Lightweight Deepfake Detection Based on Multi-Feature FusionSiddiqui Muhammad Yasir0Hyun Kim1Department of Electrical and Information Engineering, Research Center for Electrical and Information Technology, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaDepartment of Electrical and Information Engineering, Research Center for Electrical and Information Technology, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaDeepfake technology utilizes deep learning (DL)-based face manipulation techniques to seamlessly replace faces in videos, creating highly realistic but artificially generated content. Although this technology has beneficial applications in media and entertainment, misuse of its capabilities may lead to serious risks, including identity theft, cyberbullying, and false information. The integration of DL with visual cognition has resulted in important technological improvements, particularly in addressing privacy risks caused by artificially generated “deepfake” images on digital media platforms. In this study, we propose an efficient and lightweight method for detecting deepfake images and videos, making it suitable for devices with limited computational resources. In order to reduce the computational burden usually associated with DL models, our method integrates machine learning classifiers in combination with keyframing approaches and texture analysis. Moreover, the features extracted with a histogram of oriented gradients (HOG), local binary pattern (LBP), and KAZE bands were integrated to evaluate using random forest, extreme gradient boosting, extra trees, and support vector classifier algorithms. Our findings show a feature-level fusion of HOG, LBP, and KAZE features improves accuracy to 92% and 96% on FaceForensics++ and Celeb-DF(v2), respectively.https://www.mdpi.com/2076-3417/15/4/1954deepfake detectionfeature fusionHistogram of Oriented Gradients (HOG)Local Binary Pattern (LBP)KAZE descriptors
spellingShingle Siddiqui Muhammad Yasir
Hyun Kim
Lightweight Deepfake Detection Based on Multi-Feature Fusion
Applied Sciences
deepfake detection
feature fusion
Histogram of Oriented Gradients (HOG)
Local Binary Pattern (LBP)
KAZE descriptors
title Lightweight Deepfake Detection Based on Multi-Feature Fusion
title_full Lightweight Deepfake Detection Based on Multi-Feature Fusion
title_fullStr Lightweight Deepfake Detection Based on Multi-Feature Fusion
title_full_unstemmed Lightweight Deepfake Detection Based on Multi-Feature Fusion
title_short Lightweight Deepfake Detection Based on Multi-Feature Fusion
title_sort lightweight deepfake detection based on multi feature fusion
topic deepfake detection
feature fusion
Histogram of Oriented Gradients (HOG)
Local Binary Pattern (LBP)
KAZE descriptors
url https://www.mdpi.com/2076-3417/15/4/1954
work_keys_str_mv AT siddiquimuhammadyasir lightweightdeepfakedetectionbasedonmultifeaturefusion
AT hyunkim lightweightdeepfakedetectionbasedonmultifeaturefusion