CASIA OpenIR  > 模式识别实验室
Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization
Weinan Guan1,2,3,4; Wei Wang2,3,4; Jing Dong2,3,4; Bo Peng2,3,4
Source PublicationIEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
ISSN1556-6013
2024
Volume19Issue:2024Pages:5345-5356
Corresponding AuthorWang, Wei(wwang@nlpr.ia.ac.cn)
Abstract

The rapid development of face forgery technology
has posed a significant threat to information security. While
deepfake detection has proven to be an effective countermeasure,
it often struggles to detect fake images generated by unknown
forgery methods. Thus, the generalization ability of deepfake
detectors to unseen forgery data is a critical concern. Despite
many efforts aimed at discovering new forgery artifacts, they
often fail to generalize to new manipulation technologies. In this
paper, we tackle this challenge by focusing on the difference in
texture patterns between training forgeries and unseen forgeries,
which can lead to a degradation of generalization. Based on
this principle, we propose a new conjecture that encourages
deepfake detectors to reduce their sensitivity to forgery texture
patterns, thereby improving the detection performance. To this
end, we introduce an additional gradient regularization term to
the original empirical loss during training. However, computing
the Hessian matrix in the gradient calculation process of the
regularization term poses a computational complexity. In order
to overcome this issue, we optimize the formulation of the
gradient regularization term using a first-order approximation
method based on Taylor expansion and design a Perturbation
Injection Module (PIM) to simplify the implementation pro-
cess. Additionally, we provide a theoretical analysis from an
optimization perspective and explore an interesting aspect of
our method. Extensive experiments demonstrate the effectiveness
of our approach in improving the generalization ability of
deepfake detectors. Importantly, our method is orthogonal to
recent advancements in powerful backbones and training data
augmentation techniques. When combined with other effective
techniques, our method achieves state-of-the-art experimental
results.

KeywordDeepfake detection forgery texture patterns
DOI10.1109/TIFS.2024.3396064
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Program of China
Funding OrganizationNational Key Research and Development Program of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:001218694900023
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
IS Representative Paper
Sub direction classification多模态智能
planning direction of the national heavy laboratory可解释人工智能
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57493
Collection模式识别实验室
Corresponding AuthorWei Wang
Affiliation1.the School of Artificial Intelligence, University of Chinese Academy of Sciences
2.the State Key Laboratory of Multimodal Artificial Intelligence System
3.Center for Research on Intelligent Perception and Computing
4.Institute of Automation, Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Weinan Guan,Wei Wang,Jing Dong,et al. Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2024,19(2024):5345-5356.
APA Weinan Guan,Wei Wang,Jing Dong,&Bo Peng.(2024).Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,19(2024),5345-5356.
MLA Weinan Guan,et al."Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19.2024(2024):5345-5356.
Files in This Item: Download All
File Name/Size DocType Version Access License
Improving_Generaliza(1989KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Weinan Guan]'s Articles
[Wei Wang]'s Articles
[Jing Dong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Weinan Guan]'s Articles
[Wei Wang]'s Articles
[Jing Dong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Weinan Guan]'s Articles
[Wei Wang]'s Articles
[Jing Dong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Improving_Generalization_of_Deepfake_Detectors_by_Imposing_Gradient_Regularization.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.