Forensic Detection of Child Exploitation Material using Deep Learning

Mofakharul Islam, Abdun Mahmood, Paul Watters, Mamoun Alazab

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

Abstract

A precursor to successful automatic child exploitation material recognition is the ability to automatically identify pornography (largely solved) involving children (largely unsolved). Identifying children’s faces in images previously labelled as pornographic can provide a solution. Automatic child face detection plays an important role in online environments by facilitating Law Enforcing Agencies (LEA) to track online child abuse, bullying, sexual assault, but also can be used to detect cybercriminals who are targeting children to groom up them with a view of molestation later. Previous studies have investigated this problem in an attempt to identify only children faces from a pool of adult faces, which aims to extract information from the basic low- and high-level features i.e., colour, texture, skin tone, shape, facial structures etc. on child and adult faces. Typically, this is a machine learning-based architecture that accomplish a categorization task with the aim of identifying a child face, given a set of child and adult faces using classification technique based on extracted features from the training images. In this paper, we present a deep learning methodology, where machine learns the features straight away from the training images without having any information provided by humans to identify children faces. Compared to the results published in a couple of recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.
Original languageEnglish
Title of host publicationDeep Learning Applications for Cyber Security
EditorsMamoun Alazab, MingJian Tang
PublisherSpringer
Pages211-219
Number of pages9
ISBN (Electronic)978-3-030-13057-2
ISBN (Print)978-3-030-13056-5
DOIs
Publication statusPublished - 2019

Publication series

NameAdvanced Sciences and Technologies for Security Applications
PublisherSpringer International Publishing
ISSN (Print)1613-5113

Fingerprint

Face recognition
Learning systems
Skin
Textures
Color
Deep learning

Cite this

Islam, M., Mahmood, A., Watters, P., & Alazab, M. (2019). Forensic Detection of Child Exploitation Material using Deep Learning. In M. Alazab, & M. Tang (Eds.), Deep Learning Applications for Cyber Security (pp. 211-219). (Advanced Sciences and Technologies for Security Applications). Springer. https://doi.org/10.1007/978-3-030-13057-2_10
Islam, Mofakharul ; Mahmood, Abdun ; Watters, Paul ; Alazab, Mamoun. / Forensic Detection of Child Exploitation Material using Deep Learning. Deep Learning Applications for Cyber Security. editor / Mamoun Alazab ; MingJian Tang. Springer, 2019. pp. 211-219 (Advanced Sciences and Technologies for Security Applications).
@inbook{42fad8af34a149a29185ac16d59de284,
title = "Forensic Detection of Child Exploitation Material using Deep Learning",
abstract = "A precursor to successful automatic child exploitation material recognition is the ability to automatically identify pornography (largely solved) involving children (largely unsolved). Identifying children’s faces in images previously labelled as pornographic can provide a solution. Automatic child face detection plays an important role in online environments by facilitating Law Enforcing Agencies (LEA) to track online child abuse, bullying, sexual assault, but also can be used to detect cybercriminals who are targeting children to groom up them with a view of molestation later. Previous studies have investigated this problem in an attempt to identify only children faces from a pool of adult faces, which aims to extract information from the basic low- and high-level features i.e., colour, texture, skin tone, shape, facial structures etc. on child and adult faces. Typically, this is a machine learning-based architecture that accomplish a categorization task with the aim of identifying a child face, given a set of child and adult faces using classification technique based on extracted features from the training images. In this paper, we present a deep learning methodology, where machine learns the features straight away from the training images without having any information provided by humans to identify children faces. Compared to the results published in a couple of recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.",
keywords = "Child exploitation, Child pornography, Digital forensics, Intelligence analysis, Deep learning, Cybercrime",
author = "Mofakharul Islam and Abdun Mahmood and Paul Watters and Mamoun Alazab",
year = "2019",
doi = "10.1007/978-3-030-13057-2_10",
language = "English",
isbn = "978-3-030-13056-5",
series = "Advanced Sciences and Technologies for Security Applications",
publisher = "Springer",
pages = "211--219",
editor = "Mamoun Alazab and MingJian Tang",
booktitle = "Deep Learning Applications for Cyber Security",
address = "Switzerland",

}

Islam, M, Mahmood, A, Watters, P & Alazab, M 2019, Forensic Detection of Child Exploitation Material using Deep Learning. in M Alazab & M Tang (eds), Deep Learning Applications for Cyber Security. Advanced Sciences and Technologies for Security Applications, Springer, pp. 211-219. https://doi.org/10.1007/978-3-030-13057-2_10

Forensic Detection of Child Exploitation Material using Deep Learning. / Islam, Mofakharul; Mahmood, Abdun; Watters, Paul; Alazab, Mamoun.

Deep Learning Applications for Cyber Security. ed. / Mamoun Alazab; MingJian Tang. Springer, 2019. p. 211-219 (Advanced Sciences and Technologies for Security Applications).

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

TY - CHAP

T1 - Forensic Detection of Child Exploitation Material using Deep Learning

AU - Islam, Mofakharul

AU - Mahmood, Abdun

AU - Watters, Paul

AU - Alazab, Mamoun

PY - 2019

Y1 - 2019

N2 - A precursor to successful automatic child exploitation material recognition is the ability to automatically identify pornography (largely solved) involving children (largely unsolved). Identifying children’s faces in images previously labelled as pornographic can provide a solution. Automatic child face detection plays an important role in online environments by facilitating Law Enforcing Agencies (LEA) to track online child abuse, bullying, sexual assault, but also can be used to detect cybercriminals who are targeting children to groom up them with a view of molestation later. Previous studies have investigated this problem in an attempt to identify only children faces from a pool of adult faces, which aims to extract information from the basic low- and high-level features i.e., colour, texture, skin tone, shape, facial structures etc. on child and adult faces. Typically, this is a machine learning-based architecture that accomplish a categorization task with the aim of identifying a child face, given a set of child and adult faces using classification technique based on extracted features from the training images. In this paper, we present a deep learning methodology, where machine learns the features straight away from the training images without having any information provided by humans to identify children faces. Compared to the results published in a couple of recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.

AB - A precursor to successful automatic child exploitation material recognition is the ability to automatically identify pornography (largely solved) involving children (largely unsolved). Identifying children’s faces in images previously labelled as pornographic can provide a solution. Automatic child face detection plays an important role in online environments by facilitating Law Enforcing Agencies (LEA) to track online child abuse, bullying, sexual assault, but also can be used to detect cybercriminals who are targeting children to groom up them with a view of molestation later. Previous studies have investigated this problem in an attempt to identify only children faces from a pool of adult faces, which aims to extract information from the basic low- and high-level features i.e., colour, texture, skin tone, shape, facial structures etc. on child and adult faces. Typically, this is a machine learning-based architecture that accomplish a categorization task with the aim of identifying a child face, given a set of child and adult faces using classification technique based on extracted features from the training images. In this paper, we present a deep learning methodology, where machine learns the features straight away from the training images without having any information provided by humans to identify children faces. Compared to the results published in a couple of recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.

KW - Child exploitation

KW - Child pornography

KW - Digital forensics

KW - Intelligence analysis

KW - Deep learning

KW - Cybercrime

U2 - 10.1007/978-3-030-13057-2_10

DO - 10.1007/978-3-030-13057-2_10

M3 - Chapter

SN - 978-3-030-13056-5

T3 - Advanced Sciences and Technologies for Security Applications

SP - 211

EP - 219

BT - Deep Learning Applications for Cyber Security

A2 - Alazab, Mamoun

A2 - Tang, MingJian

PB - Springer

ER -

Islam M, Mahmood A, Watters P, Alazab M. Forensic Detection of Child Exploitation Material using Deep Learning. In Alazab M, Tang M, editors, Deep Learning Applications for Cyber Security. Springer. 2019. p. 211-219. (Advanced Sciences and Technologies for Security Applications). https://doi.org/10.1007/978-3-030-13057-2_10