A study of detecting child pornography on smart phone

Document Type

Article

Source of Publication

Lecture Notes on Data Engineering and Communications Technologies

Publication Date

1-1-2018

Abstract

© Springer International Publishing AG 2018. Child Pornography is an increasingly visible rising cybercrime in the world today. Over the past decade, with rapid growth in smart phone usage, readily available free Cloud Computing storage, and various mobile communication apps, child pornographers have found a convenient and reliable mobile platform for instantly sharing pictures or videos of children being sexually abused. Within this new paradigm, law enforcement officers are finding that detecting, gathering, and processing evidence for the prosecution of child pornographers is becoming increasingly challenging. Deep learning is a machine learning method that models high-level abstractions in data and extracts hierarchical representations of data by using a deep graph with multiple processing layers. This paper presents a conceptual model of deep learning approach for detecting child pornography within the new paradigm by using log analysis, file name analysis and cell site analysis which investigate text logs of events that have happened in the smart phone at the scene of the crime using physical and logical acquisition to assists law enforcement officers in gathering and processing child pornography evidence for prosecution. In addition, this paper shows an illustrative example of logical and physical acquisition on smart phones using forensics tools.

ISSN

2367-4520

Publisher

Springer International Publishing

Volume

7

First Page

373

Last Page

384

Disciplines

Computer Sciences | Social and Behavioral Sciences

Keywords

Cell site analysis, Child pornography, Conceptual model, Deep learning, File name analysis, Forensics tools, Log analysis, Logical and physical acquisition, Smart phone

Scopus ID

85090369400

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS