AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images

[EN] Nowadays, the growing number of cases of possession and distribution of Child Sexual Abuse (CSA) material pose a significant challenge for Law Enforcement Agencies (LEAs). In this paper, we decompose the automatic CSA detection problem into two simpler ones for which it is feasible to create ma...

Descripción completa

Detalles Bibliográficos
Autores: Kumar, Abhishek Gangwar, González Castro, Víctor, Alegre Gutiérrez, Enrique, Fidalgo Fernández, Eduardo
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2021
País:España
Institución:Universidad de León
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:buleria.unileon.es:10612/23125
Acceso en línea:https://hdl.handle.net/10612/23125
Access Level:acceso abierto
Palabra clave:Informática
Ingeniería de sistemas
Child sexual abuse (CSA) detection
Age-group detection
Pornography detection
Convolutional neural network (CNN)
Metric learning
Visual attention
1203.04 Inteligencia Artificial
2209.90 Tratamiento Digital. Imágenes
3304.05 Sistemas de Reconocimiento de Caracteres
1209.03 Análisis de Datos
1203.12 Bancos de Datos
id ES_137bb776c5b3a91c2ecec17c8467a938
oai_identifier_str oai:buleria.unileon.es:10612/23125
network_acronym_str ES
network_name_str España
repository_id_str
spelling AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in imagesKumar, Abhishek GangwarGonzález Castro, VíctorAlegre Gutiérrez, EnriqueFidalgo Fernández, EduardoInformáticaIngeniería de sistemasChild sexual abuse (CSA) detectionAge-group detectionPornography detectionConvolutional neural network (CNN)Metric learningVisual attention1203.04 Inteligencia Artificial2209.90 Tratamiento Digital. Imágenes3304.05 Sistemas de Reconocimiento de Caracteres1209.03 Análisis de Datos1203.12 Bancos de Datos[EN] Nowadays, the growing number of cases of possession and distribution of Child Sexual Abuse (CSA) material pose a significant challenge for Law Enforcement Agencies (LEAs). In this paper, we decompose the automatic CSA detection problem into two simpler ones for which it is feasible to create massive labeled datasets, especially to train deep neural networks: (i) pornographic content detection and (ii) age-group classification of a person as a minor or an adult. We propose a deep CNN architecture with a novel attention mechanism and metric learning, denoted as AttM-CNN, for these tasks. Furthermore, the pornography detection and the age-group classification networks are combined for CSA detection using two different strategies: decision level fusion for binary CSA classification and score level fusion for the re-arrangement of the suspicious images. We also introduce two new datasets: (i) Pornographic-2M, which contains two million pornographic images, and (ii) Juvenile-80k, including 80k manually labeled images with apparent facial age. The experiments conducted for age-group and pornographic classification demonstrate that our approach obtained similar or superior results compared to the state-of-the-art systems on various benchmark datasets for both tasks, respectively. For the evaluation of CSA detection, we created a test dataset comprising one million adult porn, one million non-porn images, and 5,000 real CSA images provided to us by Police Forces. For binary CSA classification, our method obtained an accuracy of 92.72%, which increases the recognition rate by more than 21% compared to a well-known forensic tool, i.e. NuDetective. Furthermore, re-arrangement of the CSA test dataset images showed that 80% of CSA images can be found in the top 8.5% of images in the ranked list created using our approach.SIThis research was supported by the framework agreement between the University of León and INCIBE (Spanish National Cybersecurity Institute) under Addendum 22 and 01. This research has been funded with support from the European Commission under the 4NSEEK project with Grant Agreement 821966. This publication reflects the views only of the authors, and the European Commission cannot be held responsible for any use which may be made of the information contained therein. We gratefully acknowledge the support of NVIDIA Corporation for their kind donation of GPUs which were used in this work. We are thankful to Spanish Police for providing access to the real CSA media for research purposes and to the Brazilian Federal Police Department for providing us the NuDetective software.Instituto Nacional de CiberseguridadEuropean CommissionElsevierIngenieria de Sistemas y AutomaticaEscuela de Ingenierias Industrial, Informática y Aeroespacial2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionhttps://hdl.handle.net/10612/23125reponame:BULERIA. Repositorio Institucional de la Universidad de Leóninstname:Universidad de LeónIngléshttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:buleria.unileon.es:10612/231252026-06-24T12:43:27Z
dc.title.none.fl_str_mv AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
title AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
spellingShingle AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
Kumar, Abhishek Gangwar
Informática
Ingeniería de sistemas
Child sexual abuse (CSA) detection
Age-group detection
Pornography detection
Convolutional neural network (CNN)
Metric learning
Visual attention
1203.04 Inteligencia Artificial
2209.90 Tratamiento Digital. Imágenes
3304.05 Sistemas de Reconocimiento de Caracteres
1209.03 Análisis de Datos
1203.12 Bancos de Datos
title_short AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
title_full AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
title_fullStr AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
title_full_unstemmed AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
title_sort AttM-CNN: Attention and metric learning based CNN for pornography, age and Child Sexual Abuse (CSA) Detection in images
dc.creator.none.fl_str_mv Kumar, Abhishek Gangwar
González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
author Kumar, Abhishek Gangwar
author_facet Kumar, Abhishek Gangwar
González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
author_role author
author2 González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
author2_role author
author
author
dc.contributor.none.fl_str_mv Ingenieria de Sistemas y Automatica
Escuela de Ingenierias Industrial, Informática y Aeroespacial
dc.subject.none.fl_str_mv Informática
Ingeniería de sistemas
Child sexual abuse (CSA) detection
Age-group detection
Pornography detection
Convolutional neural network (CNN)
Metric learning
Visual attention
1203.04 Inteligencia Artificial
2209.90 Tratamiento Digital. Imágenes
3304.05 Sistemas de Reconocimiento de Caracteres
1209.03 Análisis de Datos
1203.12 Bancos de Datos
topic Informática
Ingeniería de sistemas
Child sexual abuse (CSA) detection
Age-group detection
Pornography detection
Convolutional neural network (CNN)
Metric learning
Visual attention
1203.04 Inteligencia Artificial
2209.90 Tratamiento Digital. Imágenes
3304.05 Sistemas de Reconocimiento de Caracteres
1209.03 Análisis de Datos
1203.12 Bancos de Datos
description [EN] Nowadays, the growing number of cases of possession and distribution of Child Sexual Abuse (CSA) material pose a significant challenge for Law Enforcement Agencies (LEAs). In this paper, we decompose the automatic CSA detection problem into two simpler ones for which it is feasible to create massive labeled datasets, especially to train deep neural networks: (i) pornographic content detection and (ii) age-group classification of a person as a minor or an adult. We propose a deep CNN architecture with a novel attention mechanism and metric learning, denoted as AttM-CNN, for these tasks. Furthermore, the pornography detection and the age-group classification networks are combined for CSA detection using two different strategies: decision level fusion for binary CSA classification and score level fusion for the re-arrangement of the suspicious images. We also introduce two new datasets: (i) Pornographic-2M, which contains two million pornographic images, and (ii) Juvenile-80k, including 80k manually labeled images with apparent facial age. The experiments conducted for age-group and pornographic classification demonstrate that our approach obtained similar or superior results compared to the state-of-the-art systems on various benchmark datasets for both tasks, respectively. For the evaluation of CSA detection, we created a test dataset comprising one million adult porn, one million non-porn images, and 5,000 real CSA images provided to us by Police Forces. For binary CSA classification, our method obtained an accuracy of 92.72%, which increases the recognition rate by more than 21% compared to a well-known forensic tool, i.e. NuDetective. Furthermore, re-arrangement of the CSA test dataset images showed that 80% of CSA images can be found in the top 8.5% of images in the ranked list created using our approach.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10612/23125
url https://hdl.handle.net/10612/23125
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:BULERIA. Repositorio Institucional de la Universidad de León
instname:Universidad de León
instname_str Universidad de León
reponame_str BULERIA. Repositorio Institucional de la Universidad de León
collection BULERIA. Repositorio Institucional de la Universidad de León
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403678967857152
score 15.811543

Similares en LA Referencia