Predicting prolific live streaming of child sexual abuse

Photo of person sitting in front of laptop in the dark
Abstract

Technologically enabled crime has proliferated in recent years. One such crime type is the live streaming of child sexual abuse (CSA). This study employs a machine learning approach to better understand the characteristics of Australians who engaged with known facilitators of CSA live streaming in the Philippines.

This model demonstrated notable success in identifying the individuals who would engage in a high number of transactions with known facilitators.

Individuals engaged in high-volume live streaming typically spent small amounts (under $55) at intervals of less than 20 days. Where prolific offenders had a criminal record, it was unlikely to consist of high-harm crime types, such as violent or sexual offences.

References

URLs correct as at July 2021

Açar KV 2017. Webcam child prostitution: An exploration of current and futuristic methods of detection. International Journal of Cyber Criminology 11(1): 98–109. https://doi.org/10.5281/zenodo.4957

Amrit C, Paauw T, Aly R & Lavric M 2017. Identifying child abuse through text mining and machine learning. Expert Systems with Applications 88: 402–418. https://doi.org/10.1016/j.eswa.2017.06.035

Ashby MJP 2017. Comparing methods for measuring crime harm/severity. Policing: A Journal of Policy and Practice 12(4): 439–54. https://doi.org/10.1093/police/pax049

Babchishin KM, Hanson RK & Hermann CA 2011. The characteristics of online sex offenders: A meta-analysis. Sexual Abuse: A Journal of Research and Treatment 23(1): 92–123. https://doi.org/10.1177/1079063210370708

Barnes GC & Hyatt JM 2012. Classifying adult probationers by forecasting future offending: Final technical report. Washington DC: US Department of Justice. https://nij.ojp.gov/library/publications/classifying-adult-probationers-forecasting-future-offending

Berk R 2013. Algorithmic criminology. Security Informatics 2(5): 1–14. https://doi.org/10.1186/2190-8532-2-5

Brown R, Napier S & Smith RG 2020. Australians who view live streaming of child sexual abuse: An analysis of financial transactions. Trends & issues in crime and criminal justice no. 589. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti04336

Bunting LA 2014. Exploring the influence of reporting delay on criminal justice outcomes: Comparing child and adult reporters of childhood sexual abuse. Journal of Child Sexual Abuse 23(5): 577–594. https://doi.org/10.1080/10538712.2014.920457

Butler B 2019. Westpac’s CEO Brian Hartzer resigns over money-laundering scandal. The Guardian, Australia edition, 26 November. https://www.theguardian.com/australia-news/2019/nov/26/westpac-chief-executivebrian-hartzer-resigns-over-money-laundering-scandal

Choi MY & Ma C 2020. Making a big impact with small datasets using machine-learning approaches. The Lancet Rheumatology 2(8): 451–452. https://doi.org/10.1016/S2665-9913(20)30217-4

Chouldechova A, Putnam-Hornstein E, Benavides-Prado D, Fialko O & Vaithianathan R 2018. A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions. Proceedings of the 1st Conference on Fairness, Accountability and Transparency, in Proceedings of Machine Learning Research 81: 1–15

Couronné R, Probst P & Boulesteix AL 2018. Random forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinformatics 19(270): 1–14. https://doi.org/10.1186/s12859-018-2264-5

de Leon S 2013. Cyber-sex trafficking: A 21st century scourge. CNN, 18 July. https://edition.cnn.com/2013/07/17/world/asia/philippines-cybersex-trafficking/index.html

DeHart D, Dwyer G, Seto MC, Moran R, Letourneau E & Schwarz-Watts D 2017. Internet sexual solicitation of children: A proposed typology of offenders based on their chats, e-mails, and social network posts. Journal of Sexual Aggression 23(1): 77–89. https://doi.org/10.1080/13552600.2016.1241309

ECPAT International 2017. Online child sexual exploitation: An analysis of emerging and selected issues. ECPAT International Journal 12: 1–63

ECPAT International 2016. Terminology guidelines for the protection of children from sexual exploitation and sexual abuse. Luxembourg: ECPAT International

Europol 2019. Internet organised crime threat assessment 2019. The Hague: Europol. https://www.europol.europa.eu/activities-services/main-reports/internet-organised-crime-threat-assessment-iocta-2019

Gillingham P 2016. Predictive risk modelling to prevent child maltreatment and other adverse outcomes for service users: Inside the ‘black box’ of machine learning. British Journal of Social Work 46(4): 1044–1058. https://doi.org/10.1093/bjsw/bcv031

Gruenfeld E, Willis DG & Easton SD 2017. “A very steep climb”: Therapists’ perspectives on barriers to disclosure of child sexual abuse experiences for men. Journal of Child Sexual Abuse 26(6): 731–751. https://doi.org/10.1080/10538712.2017.1332704

Hong H, Xiaoling G & Hua Y 2016. Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. Paper presented at the 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)

House PD & Neyroud PW 2018. Developing a crime harm index for Western Australia: The WACHI. Cambridge Journal of Evidence-Based Policing 2(1–2): 70–94. https://doi.org/10.1007/s41887-018-0022-6

Hyndman RJ & Anthanasopoulos G 2014. Forecasting: Principles and practice. Melbourne: Monash University

Internet Watch Foundation (IWF) 2018. Trends in child sexual exploitation: Examining the distribution of captures of live-streamed child sexual abuse. Cambridge, UK: Internet Watch Foundation

Jullum M, Løland A, Huseby RB, Ånonsen G & Lorentzen J 2020. Detecting money laundering transactions with machine learning. Journal of Money Laundering Control 23(1): 173–186. https://doi.org/10.1108/JMLC-07-2019-0055

Kloess JA, Seymour-Smith S, Hamilton-Giachritsis CE, Long MLL, Shipley D & Beech AR 2015. A qualitative analysis of offenders’ modus operandi in sexually exploitative interactions with children online. Sexual Abuse 29(6): 563–591. https://doi.org/10.1177/1079063215612442

Kuhlmann DF & Aurén S 2015. Nipa huts with high speed Internet: Commercial exploitation of children in the 21st century: A qualitative investigation of webcam child prostitution in the Philippines (doctoral thesis). Lund University, Sweden. https://lup.lub.lu.se/student-papers/search/publication/5424968

Morgan A, Dowling C & Voce I 2020. Australian outlaw motorcycle gang involvement in violent and organised crime. Trends & issues in crime and criminal justice no. 586. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti04282

Puffer E, McDonald K, Pross M & Hudson D 2014. Webcam child sex tourism: An emerging global issue. https://digitalcommons.cedarville.edu/research_scholarship_symposium/2014/podium_presentations/15/

Seto MC, Hanson KR & Babchishin KM 2011. Contact sexual offending by men with online sexual offenses. Sexual Abuse: A Journal of Research and Treatment 23(1): 124–45. https://doi.org/10.1177/1079063210369013

Smith K, Bryant-Davis T, Tillman S & Marks A 2010. Stifled voices: Barriers to help-seeking behaviour for South African childhood sexual assault survivors. Journal of Child Sexual Abuse 19(3): 255–274. https://doi.org/10.1080/10538711003781269

Terre des Hommes 2014. Webcam child sex tourism: Becoming Sweetie: A novel approach to stopping the global rise of webcam child sex tourism. The Hague: Terre des Hommes. https://www.terredeshommes.org/webcam-child-sex-tourism-2/

WeProtect Global Alliance 2019. Global threat assessment 2019. London: WeProtect Global Alliance. https://www.weprotect.org/issue/global-threat-assessment/

Zhang H & Wang M 2009. Search for the smallest random forest. Statistics and its Interface 2(3): 381. https://doi.org/10.4310/sii.2009.v2.n3.a11

Zhao Q & Hastie T 2019. Causal interpretations of black box models. Journal of Business & Economic Statistics 37(1): 272–281. https://doi.org/10.1080/07350015.2019.1624293