Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Romeo, Lanzino, Federico, Fontana, Anxhelo, Diko, Raoul, Marini Marco, Luigi, Cinque
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916307975274496
author Romeo, Lanzino
Federico, Fontana
Anxhelo, Diko
Raoul, Marini Marco
Luigi, Cinque
author_facet Romeo, Lanzino
Federico, Fontana
Anxhelo, Diko
Raoul, Marini Marco
Luigi, Cinque
contents Deepfake detection aims to contrast the spread of deep-generated media that undermines trust in online content. While existing methods focus on large and complex models, the need for real-time detection demands greater efficiency. With this in mind, unlike previous work, we introduce a novel deepfake detection approach on images using Binary Neural Networks (BNNs) for fast inference with minimal accuracy loss. Moreover, our method incorporates Fast Fourier Transform (FFT) and Local Binary Pattern (LBP) as additional channel features to uncover manipulation traces in frequency and texture domains. Evaluations on COCOFake, DFFD, and CIFAKE datasets demonstrate our method's state-of-the-art performance in most scenarios with a significant efficiency gain of up to a $20\times$ reduction in FLOPs during inference. Finally, by exploring BNNs in deepfake detection to balance accuracy and efficiency, this work paves the way for future research on efficient deepfake detection.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04932
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks
Romeo, Lanzino
Federico, Fontana
Anxhelo, Diko
Raoul, Marini Marco
Luigi, Cinque
Computer Vision and Pattern Recognition
Machine Learning
Deepfake detection aims to contrast the spread of deep-generated media that undermines trust in online content. While existing methods focus on large and complex models, the need for real-time detection demands greater efficiency. With this in mind, unlike previous work, we introduce a novel deepfake detection approach on images using Binary Neural Networks (BNNs) for fast inference with minimal accuracy loss. Moreover, our method incorporates Fast Fourier Transform (FFT) and Local Binary Pattern (LBP) as additional channel features to uncover manipulation traces in frequency and texture domains. Evaluations on COCOFake, DFFD, and CIFAKE datasets demonstrate our method's state-of-the-art performance in most scenarios with a significant efficiency gain of up to a $20\times$ reduction in FLOPs during inference. Finally, by exploring BNNs in deepfake detection to balance accuracy and efficiency, this work paves the way for future research on efficient deepfake detection.
title Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2406.04932