Constructing New Backbone Networks via Space-Frequency Interactive Convolution for Deepfake Detection

Simple item page
aut.relation.endpage1
aut.relation.issue99
aut.relation.journalIEEE Transactions on Information Forensics and Security
aut.relation.startpage1
aut.relation.volumePP
dc.contributor.authorGuo, Zhiqing
dc.contributor.authorJia, Zhenhong
dc.contributor.authorWang, Liejun
dc.contributor.authorWang, Dewang
dc.contributor.authorYang, Gaobo
dc.contributor.authorKasabov, Nikola
dc.date.accessioned2023-11-08T23:19:26Z
dc.date.available2023-11-08T23:19:26Z
dc.date.issued2023-10-16
dc.description.abstractThe serious concerns over the negative impacts of Deepfakes have attracted wide attentions in the community of multimedia forensics. The existing detection works achieve deepfake detection by improving the traditional backbone networks to capture subtle manipulation traces. However, there is no attempt to construct new backbone networks with different structures for Deepfake detection by improving the internal feature representation of convolution. In this work, we propose a novel Space-Frequency Interactive Convolution (SFIConv) to efficiently model the manipulation clues left by Deepfake. To obtain high-frequency features from tampering traces, a Multichannel Constrained Separable Convolution (MCSConv) is designed as the component of the proposed SFIConv, which learns space-frequency features via three stages, namely generation, interaction and fusion. In addition, SFIConv can replace the vanilla convolution in any backbone networks without changing the network structure. Extensive experimental results show that seamlessly equipping SFIConv into the backbone network greatly improves the accuracy for Deepfake detection. In addition, the space-frequency interaction mechanism does benefit to capturing common artifact features, thus achieving better results in cross-dataset evaluation. Our code will be available at https://github.com/EricGzq/SFIConv.
dc.identifier.citationIEEE Transactions on Information Forensics and Security, ISSN: 1556-6013 (Print); 1556-6021 (Online), Institute of Electrical and Electronics Engineers (IEEE), PP(99), 1-1. doi: 10.1109/tifs.2023.3324739
dc.identifier.doi10.1109/tifs.2023.3324739
dc.identifier.issn1556-6013
dc.identifier.issn1556-6021
dc.identifier.urihttp://hdl.handle.net/10292/16891
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urihttps://ieeexplore.ieee.org/document/10286083
dc.rightsCopyright © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.rights.accessrightsOpenAccess
dc.subject46 Information and Computing Sciences
dc.subject4611 Machine Learning
dc.subject08 Information and Computing Sciences
dc.subject09 Engineering
dc.subjectStrategic, Defence & Security Studies
dc.subject40 Engineering
dc.subject46 Information and computing sciences
dc.titleConstructing New Backbone Networks via Space-Frequency Interactive Convolution for Deepfake Detection
dc.typeJournal Article
pubs.elements-id527372
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Constructing_New_Backbone_Networks_via_Space-Frequency_Interactive_Convolution_for_Deepfake_Detection.pdf
Size:
1.67 MB
Format:
Adobe Portable Document Format
Description:
Journal article
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau