A Survey of Generative AI for Detecting Pedophilia Crimes
Source abstract
Abstract
The complexity for law enforcement and child protection agencies has been exacerbated by the proliferation of child sexual exploitation channels, facilitated by digital platforms and social media. Generative AI’s ability to analyze large datasets, recognize patterns, and generate new content makes it one of the potential solutions for detecting suspicious behavior and indicators of child sexual exploitation. This paper discusses the potential of generative AI to aid in the fight against pedophilic crimes by reviewing current research, methodologies, and challenges, as well as future directions and ethical concerns. Although the potential benefits are significant, applying AI to such a sensitive area presents numerous challenges, including privacy concerns, algorithmic bias, and potential misuse, which must be addressed carefully.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital and Cyber Forensics · Crime Patterns and Interventions · Cybercrime and Law Enforcement Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Coimbra Institute of Engineering (ISEC), Polytechnic University of Coimbra, Rua Pedro Nunes—Quinta da Nora, 3030-199 Coimbra, Portugal
Centre for Informatics and Systems of the University of Coimbra (CISUC), Pólo II, Pinhal de Marrocos, 3030-290 Coimbra, Portugal
FATEC—Faculdade de Tecnologia de Mogi das Cruzes, São Paulo Technological College, Mogi das Cruzes 08773-600, Brazil
References (46)
Show source-provided references
1. Marvasti, J.A. (2004). Psychiatric Treatment of Sexual Offenders: Treating the Past Traumas in Traumatizers. A Bio-Psycho-Social Perspective, Charles C Thomas Publisher.
2. Cook, D., Zilka, M., DeSandre, H., Giles, S., Weller, A., and Maskell, S. (2022). Can We Automate the Analysis of Online Child Sexual Exploitation Discourse?. arXiv.
3. Artificial intelligence and child sexual abuse: A rapid evidence assessment
4. Levy, I., and Robinson, C. (2022). Thoughts on child safety on commodity platforms. arXiv.
5. UNICRI—United Nations Interregional Crime and Justice Research Institute (2025, May 06). New! How AI Is Leading the Fight Against Online Child Abuse. Available online: https://unicri.org/News/AI-for-Safer-Children-%20article-Emerging-Europe.
6. Puentes, J., Castillo, A., Osejo, W., Calderón, Y., Quintero, V., and Saldarriaga, L. (2023, January 2–6). Guarding the Guardians: Automated Analysis of Online Child Sexual Abuse. Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France.10.1109/ICCVW60793.2023.00400 ↗
7. Online grooming detection: A comprehensive survey of child exploitation in chat logs10.1016/j.knosys.2022.110039 ↗
8. An effective hybrid collaborative algorithm for energy-efficient distributed permutation flow-shop inverse scheduling10.1016/j.future.2021.10.003 ↗
9. Identification of red flag child sexual grooming behaviors10.1016/j.chiabu.2022.105998 ↗
10. Rani, G., Singh, J., and Khanna, A. (2023, January 23–24). Comparative Analysis of Generative AI Models. Proceedings of the 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), Faridabad, India.10.1109/ICAICCIT60255.2023.10465941 ↗
11. Prosser, E., and Edwards, M. (2024, January 5–6). Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention. Proceedings of the EICC 2024: European Interdisciplinary Cybersecurity Conference, Xanthi, Greece.10.1145/3655693.3655694 ↗
12. Gemini versus ChatGPT: Applications, performance, architecture, capabilities, and implementation10.48185/jaai.v5i1.1052 ↗
13. Buscemi, A., and Proverbio, D. (2024). ChatGPT vs Gemini vs LLaMA on Multilingual Sentiment Analysis. arXiv.
14. Detecting online grooming at its earliest stages: Development and validation of the Online Grooming Risk Scale
15. Learning to Identify Internet Sexual Predation10.2753/JEC1086-4415150305 ↗
16. Upadhyay, A., Chaudhari, A., Ghale, S., and Pawar, S.S. (2017, January 19–20). Detection and prevention measures for cyberbullying and online grooming. Proceedings of the 2017 International Conference on Inventive Systems and Control (ICISC), Coimbatore, India.10.1109/ICISC.2017.8068605 ↗
17. Keyvanpour, M., Nayebi, N.G., Ebrahimi, M., Ormandjieva, O., and Suen, C.Y. (2016). Automated identification of child abuse in chat rooms by using data mining. Data Mining Trends and Applications in Criminal Science and Investigations, IGI Global.10.4018/978-1-5225-0463-4.ch009 ↗
18. Ngejane, C.H., Mabuza-Hocquet, G., Eloff, J.H.P., and Lefophane, S. (2018, January 6–7). Mitigating Online Sexual Grooming Cyber-crime on Social Media Using Machine Learning: A Desktop Survey. Proceedings of the 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD), Durban, South Africa.10.1109/ICABCD.2018.8465413 ↗
19. Anderson, P., Zuo, Z., Yang, L., and Qu, Y. (2019, January 23–26). An Intelligent Online Grooming Detection System Using AI Technologies. Proceedings of the 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), New Orleans, LA, USA.10.1109/FUZZ-IEEE.2019.8858973 ↗
20. Logistic Models for Classifying Online Grooming Conversation10.1016/j.procs.2015.07.536 ↗
21. Fauzi, M.A., Wolthusen, S., Yang, B., Bours, P., and Yeng, P. (2023, January 16–18). Identifying Sexual Predators in Chats Using SVM and Feature Ensemble. Proceedings of the 2023 International Conference on Emerging Trends in Networks and Computer Communications (ETNCC), Windhoek, Namibia.10.1109/ETNCC59188.2023.10284950 ↗
22. Detecting predatory conversations in social media by deep Convolutional Neural Networks10.1016/j.diin.2016.07.001 ↗
23. Identifying Online Sexual Grooming Content in Social Media Using Classification Technique
24. Mila, K.C., Montreal, H., Caporossi, G., Rabbany, R., De Cock, M., and Mila, G.F. (2025, May 06). Early Detection of Sexual Predators with Federated Learning. May 2023. Available online: https://openreview.net/pdf?id=M84OnT0ZvDq.
25. Eilifsen, T.N., Shrestha, B., and Bours, P. (2023, January 26–27). Early Detection of Cyber Grooming in Online Conversations: A Dynamic Trust Model and Sliding Window Approach. Proceedings of the 2023 21st International Conference on Emerging eLearning Technologies and Applications (ICETA), Stary Smokovec, Slovakia.10.1109/ICETA61311.2023.10343952 ↗
26. Liu, D., Suen, C.Y., and Ormandjieva, O. (2017). A Novel Way of Identifying Cyber Predators. arXiv.
27. Vogt, M., Leser, U., and Akbik, A. (2021, January 1–6). Early detection of sexual predators in chats. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Bangkok, Thailand.10.18653/v1/2021.acl-long.386 ↗
28. Simen, M.A. (2023). Fine Tuning BERT for Detecting Cyber Grooming in Online Chats. [Master’s Thesis, Norwegian University of Science and Technology]. Available online: https://ntnuopen.ntnu.no/ntnu-xmlui/handle/11250/3088473.
29. Borj, P.R., Raja, K., and Bours, P. (2023, January 26). Detecting Online Grooming by Simple Contrastive Chat Embeddings. Proceedings of the Thirteenth ACM Conference on Data and Application Security and Privacy, Charlotte, NC, USA.
30. Nguyen, T.T., Wilson, C., and Dalins, J. (2024, January 9–11). Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium.10.14428/esann/2024.ES2024-222 ↗
31. Deep Learning-Based Natural Language Processing Model and Optical Character Recognition for Detection of Online Grooming on Social Networking Services
32. Kim, D., Kim, T., and Yang, J. (April, January 31). Early Detection of Online Grooming with Language Models. Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, Catania International Airport, Catania, Italy.
33. Hamm, L. (2025). Advancing Grooming Detection in Chat Logs: Comparing Traditional Machine Learning and Large Language Models with a Focus on Predator Tone. [Master’s Thesis, Uppsala University]. Available online: https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-550352.
34. Metadata-Based Detection of Child Sexual Abuse Material10.1109/TDSC.2023.3324275 ↗
35. Struckman, K. (2025, May 06). Wilson Center. Combatting AI-Generated CSAM. February 2023. Available online: https://www.wilsoncenter.org/article/combatting-ai-generated-csam.
36. European Parliament (2025, May 06). Children and Generative AI. February 2025. Available online: https://www.europarl.europa.eu/thinktank/en/document/EPRS_ATA(2025)769494.
37. Hua, Y., Namavari, A., Cheng, K., Naaman, M., and Ristenpart, T. (2022, January 10–12). Increasing Adversarial Uncertainty to Scale Private Similarity Testing. Proceedings of the 31st USENIX Security Symposium, Boston, MA, USA. Available online: https://www.usenix.org/system/files/sec22summer_hua.pdf.
38. Liang, P.P., Wu, C., Morency, L.P., and Salakhutdinov, R. (2021, January 18–24). Towards Understanding and Mitigating Social Biases in Language Models. Proceedings of the 38th International Conference on Machine Learning, Virtual. Available online: https://arxiv.org/pdf/2106.13219.
39. (2025, May 06). Monash University. Digital Child Abuse: Deepfakes and the Rising Danger of AI-Generated Exploitation. February 2025. Available online: https://lens.monash.edu/@politics-society/2025/02/25/1387341/digital-child-abuse-deepfakes-and-the-rising-danger-of-ai-generated-exploitation.
40. (2025, May 06). GOV.UK. Innovating to Detect Deepfakes and Protect the Public. February 2023, Available online: https://www.gov.uk/government/case-studies/innovating-to-detect-deepfakes-and-protect-the-public.
41. Bang, Y., Ji, Z., Schelten, A., Hartshorn, A., Fowler, T., Zhang, C., Cancedda, N., and Fung, P. (2025). HalluLens: LLM Hallucination Benchmark. arXiv, Available online: https://arxiv.org/pdf/2504.17550.
42. EUCPN—European Crime Prevention Network (2025, May 06). Artificial Intelligence and Predictive Policing: Risks and Challenges. June 2022. Available online: https://www.eucpn.org/document/recommendation-paper-artificial-intelligence-and-predictive-policing-risks-and-challenges.
43. (2025, May 06). GlobeNewswire. Multimodal AI at a Crossroads: Report Reveals CSEM Risks. May 2025. Available online: https://www.globenewswire.com/news-release/2025/05/08/3077301/0/en/Multimodal-AI-at-a-Crossroads-Report-Reveals-CSEM-Risks.html.
44. Coelho, T., Ribeiro, L.S.F., Macedo, J., Santos, J.A.D., and Avila, S. (2025). Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models. arXiv, Available online: https://arxiv.org/pdf/2505.06621v1.10.1145/3715275.3732102 ↗
45. Bilal, A., Ebert, D., and Lin, B. (2025). LLMs for Explainable AI: A Comprehensive Survey. arXiv.
46. European Parliament (2025, May 06). Artificial Intelligence Act: MEPs Adopt Landmark Law. Press Release, 13 March 2024. Available online: https://www.europarl.europa.eu/news/en/press-room/20240308IPR19015/artificial-intelligence-act-meps-adopt-landmark-law.