Determining Child Sexual Abuse Posts based on Artificial Intelligence

Susan McKeever; Christina Thorpe; Vuong Ngo

doi:10.21427/s3gq-3536

Determining Child Sexual Abuse Posts based on Artificial Intelligence

Susan McKeever, Christina Thorpe, Vuong Ngo

Research output: Contribution to conference › Paper › peer-review

Abstract

The volume of child sexual abuse materials (CSAM) created and shared daily both surface web platforms such as Twitter and dark web forums is very high. Based on volume, it is not viable for human experts to intercept or identify CSAM manually. However, automatically detecting and analysing child sexual abusive language in online text is challenging and time-intensive, mostly due to the variety of data formats and privacy constraints of hosting platforms. We propose a CSAM detection intelligence algorithm based on natural language processing and machine learning techniques. Our CSAM detection model is not only used to remove CSAM on online platforms, but can also help determine perpetrator behaviours, provide evidences, and extract new knowledge for hotlines, child agencies, education programs and policy makers.

Original language	English
DOIs	https://doi.org/10.21427/s3gq-3536
Publication status	Published - 2023
Event	2023 International Society for the Prevention of Child Abuse & Neglect Congress - Edinburgh, United Kingdom Duration: 24 Sep 2023 → 27 Sep 2023

Conference

Conference	2023 International Society for the Prevention of Child Abuse & Neglect Congress
Country/Territory	United Kingdom
City	Edinburgh
Period	24/09/23 → 27/09/23
Other	ISPCAN-2023

Keywords

child sexual abuse materials
CSAM
artificial intelligence
natural language processing
machine learning
online platforms
perpetrator behaviours
evidences
hotlines
child agencies
education programs
policy makers

Access to Document

10.21427/s3gq-3536Licence: CC BY-NC-SA

Cite this

@conference{9eee96f5e6234b6eb4f35b05335fa2df,

title = "Determining Child Sexual Abuse Posts based on Artificial Intelligence",

abstract = "The volume of child sexual abuse materials (CSAM) created and shared daily both surface web platforms such as Twitter and dark web forums is very high. Based on volume, it is not viable for human experts to intercept or identify CSAM manually. However, automatically detecting and analysing child sexual abusive language in online text is challenging and time-intensive, mostly due to the variety of data formats and privacy constraints of hosting platforms. We propose a CSAM detection intelligence algorithm based on natural language processing and machine learning techniques. Our CSAM detection model is not only used to remove CSAM on online platforms, but can also help determine perpetrator behaviours, provide evidences, and extract new knowledge for hotlines, child agencies, education programs and policy makers.",

keywords = "child sexual abuse materials, CSAM, artificial intelligence, natural language processing, machine learning, online platforms, perpetrator behaviours, evidences, hotlines, child agencies, education programs, policy makers",

author = "Susan McKeever and Christina Thorpe and Vuong Ngo",

year = "2023",

doi = "10.21427/s3gq-3536",

language = "English",

note = "2023 International Society for the Prevention of Child Abuse & Neglect Congress ; Conference date: 24-09-2023 Through 27-09-2023",

}

TY - CONF

T1 - Determining Child Sexual Abuse Posts based on Artificial Intelligence

AU - McKeever, Susan

AU - Thorpe, Christina

AU - Ngo, Vuong

PY - 2023

Y1 - 2023

N2 - The volume of child sexual abuse materials (CSAM) created and shared daily both surface web platforms such as Twitter and dark web forums is very high. Based on volume, it is not viable for human experts to intercept or identify CSAM manually. However, automatically detecting and analysing child sexual abusive language in online text is challenging and time-intensive, mostly due to the variety of data formats and privacy constraints of hosting platforms. We propose a CSAM detection intelligence algorithm based on natural language processing and machine learning techniques. Our CSAM detection model is not only used to remove CSAM on online platforms, but can also help determine perpetrator behaviours, provide evidences, and extract new knowledge for hotlines, child agencies, education programs and policy makers.

AB - The volume of child sexual abuse materials (CSAM) created and shared daily both surface web platforms such as Twitter and dark web forums is very high. Based on volume, it is not viable for human experts to intercept or identify CSAM manually. However, automatically detecting and analysing child sexual abusive language in online text is challenging and time-intensive, mostly due to the variety of data formats and privacy constraints of hosting platforms. We propose a CSAM detection intelligence algorithm based on natural language processing and machine learning techniques. Our CSAM detection model is not only used to remove CSAM on online platforms, but can also help determine perpetrator behaviours, provide evidences, and extract new knowledge for hotlines, child agencies, education programs and policy makers.

KW - child sexual abuse materials

KW - CSAM

KW - artificial intelligence

KW - natural language processing

KW - machine learning

KW - online platforms

KW - perpetrator behaviours

KW - evidences

KW - hotlines

KW - child agencies

KW - education programs

KW - policy makers

U2 - 10.21427/s3gq-3536

DO - 10.21427/s3gq-3536

M3 - Paper

T2 - 2023 International Society for the Prevention of Child Abuse & Neglect Congress

Y2 - 24 September 2023 through 27 September 2023

ER -

Determining Child Sexual Abuse Posts based on Artificial Intelligence

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this