ResearchSpace

Digital forensics supported by machine learning for the detection of online sexual predatory chats

Show simple item record

dc.contributor.author Ngejane, Hombakazi C
dc.contributor.author Eloff, JHP
dc.contributor.author Sefara, Tshephisho J
dc.contributor.author Marivate, VN
dc.date.accessioned 2021-04-10T11:05:27Z
dc.date.available 2021-04-10T11:05:27Z
dc.date.issued 2021-03
dc.identifier.citation Ngejane, H.C., Eloff, J., Sefara, T.J. & Marivate, V. 2021. Digital forensics supported by machine learning for the detection of online sexual predatory chats. <i>Forensic science international: Digital investigation, 36.</i> http://hdl.handle.net/10204/11966 en_ZA
dc.identifier.issn 2666-2817
dc.identifier.uri https://doi.org/10.1016/j.fsidi.2021.301109
dc.identifier.uri https://www.sciencedirect.com/science/article/pii/S2666281721000032
dc.identifier.uri http://hdl.handle.net/10204/11966
dc.description.abstract Chat-logs are informative digital footprints available on Social Media Platforms (SMPs). With the rise of cybercrimes targeting children, chat-logs can be used to discover and flag harmful behaviour for the attention of law enforcement units. This can make an important contribution to the safety of minors on SMPs from being exploited by online predators. The problem is that digital forensic investigation is mostly manual. Thus, a daunting task for forensic investigators because of the sheer volume and variety of data. The solution that is proposed in this paper employs a Digital Forensic Process Model that is supported by Machine Learning (ML) methods to facilitate the automatic discovery of harmful conversations in chat-logs. ML has already been successfully applied in the domain of text analysis for the discovery of online sexual predatory chats. However, there is an absence of approaches that show how ML can contribute to a digital forensic investigation. Thus, the contribution of this paper is to indicate how the tasks in a digital forensic investigation process can be organised so to obtain useable ML results when investigating online predators. en_US
dc.format Abstract en_US
dc.language.iso en en_US
dc.source Forensic science international: Digital investigation, 36 en_US
dc.subject Cyber safety en_US
dc.subject Cybersecurity en_US
dc.subject Digital forensic investigation en_US
dc.subject Machine learning en_US
dc.subject Online sexual predatory conversation en_US
dc.title Digital forensics supported by machine learning for the detection of online sexual predatory chats en_US
dc.type Article en_US
dc.description.pages 11pp en_US
dc.description.note /© 2021 Elsevier Ltd. All rights reserved. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website: https://www.sciencedirect.com/science/article/pii/S2666281721000032 en_US
dc.description.cluster Defence and Security en_US
dc.description.cluster Next Generation Enterprises & Institutions
dc.description.impactarea Information Security Centre en_US
dc.description.impactarea Data Science
dc.identifier.apacitation Ngejane, H. C., Eloff, J., Sefara, T. J., & Marivate, V. (2021). Digital forensics supported by machine learning for the detection of online sexual predatory chats. <i>Forensic science international: Digital investigation, 36</i>, http://hdl.handle.net/10204/11966 en_ZA
dc.identifier.chicagocitation Ngejane, Hombakazi C, JHP Eloff, Tshephisho J Sefara, and VN Marivate "Digital forensics supported by machine learning for the detection of online sexual predatory chats." <i>Forensic science international: Digital investigation, 36</i> (2021) http://hdl.handle.net/10204/11966 en_ZA
dc.identifier.vancouvercitation Ngejane HC, Eloff J, Sefara TJ, Marivate V. Digital forensics supported by machine learning for the detection of online sexual predatory chats. Forensic science international: Digital investigation, 36. 2021; http://hdl.handle.net/10204/11966. en_ZA
dc.identifier.ris TY - Article AU - Ngejane, Hombakazi C AU - Eloff, JHP AU - Sefara, Tshephisho J AU - Marivate, VN AB - Chat-logs are informative digital footprints available on Social Media Platforms (SMPs). With the rise of cybercrimes targeting children, chat-logs can be used to discover and flag harmful behaviour for the attention of law enforcement units. This can make an important contribution to the safety of minors on SMPs from being exploited by online predators. The problem is that digital forensic investigation is mostly manual. Thus, a daunting task for forensic investigators because of the sheer volume and variety of data. The solution that is proposed in this paper employs a Digital Forensic Process Model that is supported by Machine Learning (ML) methods to facilitate the automatic discovery of harmful conversations in chat-logs. ML has already been successfully applied in the domain of text analysis for the discovery of online sexual predatory chats. However, there is an absence of approaches that show how ML can contribute to a digital forensic investigation. Thus, the contribution of this paper is to indicate how the tasks in a digital forensic investigation process can be organised so to obtain useable ML results when investigating online predators. DA - 2021-03 DB - ResearchSpace DP - CSIR J1 - Forensic science international: Digital investigation, 36 KW - Cyber safety KW - Cybersecurity KW - Digital forensic investigation KW - Machine learning KW - Online sexual predatory conversation LK - https://researchspace.csir.co.za PY - 2021 SM - 2666-2817 T1 - Digital forensics supported by machine learning for the detection of online sexual predatory chats TI - Digital forensics supported by machine learning for the detection of online sexual predatory chats UR - http://hdl.handle.net/10204/11966 ER - en_ZA
dc.identifier.worklist 24283 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record