Advancing child sexual abuse investigations using biometrics and social network analysis

person typing on laptop

This paper demonstrates how biometric features can be extracted from people in child sexual abuse material (CSAM) and examined using social network analysis to reveal important patterns across seized media files. Using an automated software system previously developed by the research team (the Biometric Analyser and Network Extractor), we extract, match and plot multiple biometric attributes (face and voice) from a database of CSAM videos compiled by law enforcement. We apply a series of network measures to illustrate how the biometric match data can be used to rapidly pinpoint key media files associated with an investigation, without the need for an investigator to manually review and catalogue all files. Future directions for this research are also discussed.


URLs correct as at November 2022

Bennabhaktula GS, Alegre E, Karastoyanova D & Azzopardi G 2020. Device-based image matching with similarity learning by convolutional neural networks that exploit the underlying camera sensor pattern noise. In M De Marsico, GS di Baja & A Fred (eds), Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods: Volume 1. SciTePress: 578–584.

Borgatti SP, Everett MG & Johnson JC 2018. Analyzing social networks, 2nd ed. Los Angeles: SAGE

Bourke ML & Craun SW 2014. Secondary traumatic stress among Internet Crimes Against Children Task Force personnel. Sexual Abuse: A Journal of Research and Treatment 26(6): 586–609.

Brewer R 2017. Controlling crime through networks. In P Drahos (ed), Regulation, institutions and networks. ANU Press: 447–464.

Bright D, Brewer R & Morselli C 2021. Using social network analysis to study crime: Navigating the challenges of criminal justice records. Social Networks 66: 50–64.

​​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.

Burns CM, Morley J, Bradshaw R & Domene J 2008. The emotional impact on coping strategies employed by police teams investigating internet child exploitation. Traumatology 14(2): 20–31.

Bursztein E, Clarke E, DeLaune M, Elifff DM, Hsu N, Olson L, Shehan J, Thakur M, Thomas K & Bright T 2019. Rethinking the detection of child sexual abuse imagery on the internet. World Wide Web Conference, 13 May, pp 2601–2607.

Canadian Centre for Child Protection 2017. International Survivors’ Survey.

Dance GJX & Keller MH 2020. Tech companies detect a surge in online videos of child sexual abuse. New York Times, 20 February.

Huang GB, Ramesh M, Berg T & Learned-Miller E 2007. Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments. Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition.

Interpol 2018. Towards a global indicator on unidentified victims in child sexual exploitation material: Technical report.

King DE 2009. Dlib-ml: A Machine Learning Toolkit. Journal of Machine Learning Research 10: 1755–1758

Krone T 2004. A typology of online child pornography offending. Trends & issues in crime and criminal justice no. 279. Canberra: Australian Institute of Criminology.

Lyons B & Epstein B 2021. Source identification of unknown video files. National Cyber Crime Conference, May, online

Lyons B & Epstein B 2020. The truth in video files: Introducing a novel approach to video source identification/authentication. VirtualLEVA Digital Multimedia Evidence Training Symposium, 26 October, online

Macedo J, Costa F & dos Santos JA 2018. A benchmark methodology for child pornography detection. 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Paraná, Brazil, pp 455–462.

Marin A & Wellman B 2011. Social network analysis: An introduction. In P Carrington & J Scott (eds), The SAGE handbook of social network analysis. Sage: 11–25.

Maxim D, Orlando S, Skinner K & Broadhurst R 2016. Online child exploitation material: Trends and emerging issues. Canberra: Australian National University Cybercrime Observatory and Office of the Children’s eSafety Commissioner.

Morselli C 2009. Inside criminal networks. New York: Springer.

Moser A, Rybnicek M & Haslinger D 2015. Challenges and limitations concerning automatic child pornography classification. Proceedings of the 10th International Conference on Computer Vision Theory and Applications, Berlin, pp 492–497.

National Center for Missing & Exploited Children 2022. 2021 our impact.

Powell M, Cassematis P, Benson M, Smallbone S & Wortley R 2015. Police officers’ perceptions of their reactions to viewing internet child exploitation material. Journal of Police and Criminal Psychology 30(2): 103–111.

Sae-Bae N, Sun X, Sencar HT & Memon ND 2014. Towards automatic detection of child pornography. 2014 IEEE International Conference on Image Processing, Paris, pp 5332–5336.

Salter M & Whitten T 2022. A comparative content analysis of pre-internet and contemporary child sexual abuse material. Deviant Behavior 43(9): 1120–1134.

Sanchez L, Grajeda C, Baggili I & Hall C 2019. A practitioner survey exploring the value of forensic tools, AI, filtering, & safer presentation for investigating child sexual abuse material (CSAM). Digital Investigation 29: 124–142.

Seigfried-Spellar KC 2018. Assessing the psychological well-being and coping mechanisms of law enforcement investigators vs. digital forensic examiners of child pornography investigations. Journal of Police and Criminal Psychology 33(3): 215–226.

Seto MC, Buckman C, Dwyer RG & Quayle E 2018. Production and active trading of child sexual exploitation images depicting identified victims. National Center for Missing & Exploited Children and Thorn.

Tejeiro R, Alison L, Hendricks E, Giles S, Long M & Shipley D 2020. Sexual behaviours in indecent images of children: A content analysis. International Journal of Cyber Criminology 14(1): 121–138.

Timmerman D, Bennabhaktula S, Alegre E & Azzopardi G 2021. Video camera identification from sensor pattern noise with a constrained ConvNet. In M De Marsico, GS di Baja & A Fred (eds), Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods: Volume 1. SciTePress: 417–425.

Wasserman S & Faust K 1994. Social network analysis: Methods and applications. Cambridge University Press.

Westlake BG & Bouchard M 2016. Liking and hyperlinking: Community detection in online child sexual exploitation networks. Social Science Research 50: 23–36.

Westlake BG, Brewer R, Swearingen T, Ross A, Patterson S, Michalski D, Hole M, Logos K, Frank R, Bright D & Afana E 2022. Developing automated methods to detect and match face and voice biometrics in child sexual abuse videos. Trends & issues in crime and criminal justice no. 648. Canberra: Australian Institute of Criminology.

Westlake BG & Frank R 2016. Seeing the forest through the trees: Identifying key players in online child sexual exploitation distribution networks. In T Holt (ed), Cybercrime through an interdisciplinary lens. Routledge: 189–209.

Yiallourou E, Demetriou R & Lanitis A 2017. On the detection of images containing child-pornographic material. 24th International Conference on Telecommunications, Cyprus. ICT.2017.7998260