Logo do repositório
 
Publicação

Detection of Forged Images Using a Combination of Passive Methods Based on Neural Networks

2024-03-14Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorAlencar, Ancilon Leuch
dc.contributor.authorLopes, Marcelo Dornbusch
dc.contributor.authorFernandes , Anita Maria da Rocha
dc.contributor.authorAnjos, Julio Cesar Santos dos
dc.contributor.authorSantana, Juan Francisco De Paz
dc.contributor.authorLeithardt, Valderi Reis Quietinho
dc.contributor.institutionCTS - Centro de Tecnologia e Sistemas
dc.contributor.institutionUNINOVA-Instituto de Desenvolvimento de Novas Tecnologias
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2024-09-30T22:34:40Z
dc.date.available2024-09-30T22:34:40Z
dc.date.issued2024-03-14
dc.description2020/09706-7) São Paulo Research Foundation (FAPESP), FAPESP–MCTIC-CGI.BR in partnership with Hapvida NotreDame Intermedica Group. Publisher Copyright: © 2024 by the authors.
dc.description.abstractIn the current era of social media, the proliferation of images sourced from unreliable origins underscores the pressing need for robust methods to detect forged content, particularly amidst the rapid evolution of image manipulation technologies. Existing literature delineates two primary approaches to image manipulation detection: active and passive. Active techniques intervene preemptively, embedding structures into images to facilitate subsequent authenticity verification, whereas passive methods analyze image content for traces of manipulation. This study presents a novel solution to image manipulation detection by leveraging a multi-stream neural network architecture. Our approach harnesses three convolutional neural networks (CNNs) operating on distinct data streams extracted from the original image. We have developed a solution based on two passive detection methodologies. The system utilizes two separate streams to extract specific data subsets, while a third stream processes the unaltered image. Each net independently processes its respective data stream, capturing diverse facets of the image. The outputs from these nets are then fused through concatenation to ascertain whether the image has undergone manipulation, yielding a comprehensive detection framework surpassing the efficacy of its constituent methods. Our work introduces a unique dataset derived from the fusion of four publicly available datasets, featuring organically manipulated images that closely resemble real-world scenarios. This dataset offers a more authentic representation than other state-of-the-art methods that use algorithmically generated datasets based on image patches. By encompassing genuine manipulation scenarios, our dataset enhances the model’s ability to generalize across varied manipulation techniques, thereby improving its performance in real-world settings. After training, the merged approach obtained an accuracy of 89.59% in the set of validation images, significantly higher than the model trained with only unaltered images, which obtained 78.64%, and the two other models trained using images with a feature selection method applied to enhance inconsistencies that obtained 68.02% for Error-Level Analysis images and 50.70% for the method using Discrete Wavelet Transform. Moreover, our proposed approach exhibits reduced accuracy variance compared to alternative models, underscoring its stability and robustness across diverse datasets. The approach outlined in this work needs to provide information about the specific location or type of tempering, which limits its practical applications.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent20
dc.format.extent1881089
dc.identifier.doi10.3390/fi16030097
dc.identifier.issn1999-5903
dc.identifier.otherPURE: 100329222
dc.identifier.otherPURE UUID: 05e2a7ac-2458-48fa-a64a-bb659710e5f4
dc.identifier.otherScopus: 85188791811
dc.identifier.otherWOS: 001191706500001
dc.identifier.urihttp://hdl.handle.net/10362/172768
dc.identifier.urlhttps://www.scopus.com/pages/publications/85188791811
dc.language.isoeng
dc.peerreviewedyes
dc.relationinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00066%2F2020/PT
dc.relationCentre of Technology and Systems
dc.relationCentre of Technology and Systems
dc.relationFunding Information: The authors would like to acknowledge the support provided by the Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina (Fapesc) under the project FAPESC Nº 29/2021-Programa Estruturante Acadêmico-Apoio à Infraestrutura de Laboratórios Acadêmicos do Estado de Santa Catarina. This support was partial and significantly contributed to the success of this research. Finally, the authors would like to acknowledge the CAPES Finance Code 001. Also, partial funding for this research was provided by the CEREIA Project (
dc.subjectconvolutional neural network
dc.subjectdeep learning
dc.subjectdigital image forensics
dc.subjectComputer Networks and Communications
dc.titleDetection of Forged Images Using a Combination of Passive Methods Based on Neural Networksen
dc.typejournal article
degois.publication.issue3
degois.publication.titleFuture Internet
degois.publication.volume16
dspace.entity.typePublication
oaire.awardNumberUIDB/00066/2020
oaire.awardNumberUIDP/00066/2020
oaire.awardTitleCentre of Technology and Systems
oaire.awardTitleCentre of Technology and Systems
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00066%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00066%2F2020/PT
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccess
relation.isProjectOfPublication779ae807-14a4-4e58-87e2-6dd81eb7a030
relation.isProjectOfPublication1d2038a0-e83e-4e7d-b885-ec08a407735c
relation.isProjectOfPublication.latestForDiscovery779ae807-14a4-4e58-87e2-6dd81eb7a030

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Detection_of_Forged_Images_Using_a_Combination_of_Passive.pdf
Tamanho:
1.79 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)