Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection

In recent years, DeepFake technologies have seen widespread adoption in various domains, including entertainment and film production. However, they have also been maliciously employed for disseminating false information and engaging in video fraud. Existing detection methods often experience signifi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on dependable and secure computing 2024-09, Vol.21 (5), p.5029-5045
Main Authors: Yu, Chuer, Zhang, Xuhong, Duan, Yuxuan, Yan, Senbo, Wang, Zonghui, Xiang, Yang, Ji, Shouling, Chen, Wenzhi
Format: Article
Language:English
Subjects:
Deception
Deepfake
Deepfakes
Face forgery detection
Faces
Feature extraction
Forgery
generalization ability
identity difference
Image quality
Performance degradation
Robustness
Shape
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, DeepFake technologies have seen widespread adoption in various domains, including entertainment and film production. However, they have also been maliciously employed for disseminating false information and engaging in video fraud. Existing detection methods often experience significant performance degradation when confronted with unknown forgeries or exhibit limitations when dealing with low-quality images. To address this challenge, we introduce Diff-ID , a novel approach designed to elucidate and quantify the identity loss induced by facial manipulations. When assessing the authenticity of an image, Diff-ID leverages a genuine image of the same individual as a reference and processes two images jointly. It aligns the reference image and the test image into the same identity-insensitive attribute feature space using a face-swapping generator. This alignment allows us to observe the identity disparities between the two images through the differences in the aligned generation pairs. Subsequently, we have developed a custom metric designed to quantify the identity loss relative to the reference image in the test image. This metric effectively distinguishes forgery images from the real ones. Extensive experiments have demonstrated the exceptional performance of our approach. It achieves a high level of detection accuracy on DeepFake images and showcases state-of-the-art generalization capabilities when confronted with previously unknown forgery methods. Moreover, it exhibits robustness even in the presence of image distortions.
ISSN:1545-5971
1941-0018
DOI:10.1109/TDSC.2024.3364679