Computer vision-based CSAM screenin
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13766Keywords:
Machine learning, Criminality, Image processingAbstract
The detection of Child Sexual Abuse Material (CSAM) is a major challenge in digital forensics and child protection, while research in this area is constrained by legal, ethical, and privacy restrictions. This paper presents a modular computer vision pipeline for CSAM risk screening based on three proxy visual signals: face detection, apparent age estimation, and adult-content classification. The system integrates YOLOv12n-face, SwinFace, and a ViT-B/16-based pornography classifier, applying a decision rule that flags an image only when evidence of adult content coexists with facial evidence suggesting a possible minor. In addition, two three-class proxy datasets, APD-2M-3C and NPDI-2K-3C, are introduced to distinguish pornographic images, simple non-pornographic images, and challenging non-pornographic images. Since no real CSAM was used, the evaluation focuses on processing performance and false-positive behavior on CSAM-free datasets. Preliminary results show that the pipeline can efficiently process large-scale image collections, although further validation with controlled law-enforcement datasets is required before operational deployment.
References
1| Amirgaliyev, B., Mussabek, M., Rakhimzhanova, T., Zhumadillayeva, A. (2025). A review of machine learning and deep learning methods for person detection, tracking and identification, and face recognition with applications. Sensors 25. DOI: 10.3390/S25051410
2| Avila, S., Thome, N., Cord, M., Valle, E., ArauJo, A. D. A. (2013). Pooling in image representation: The visual codeword point of view. Computer Vision and Image Understanding 117(5), 453–465.
3| Coelho, T., Ribeiro, L. S. F., Macedo, J., dos Santos, J. A., Avila, S. (2024). Transformers-based few-shot learning for scene classification in child sexual abuse imagery. XXXVII Conference on Graphics, Patterns and Images (SIBGRAPI Estendido 2024), pp. 8–14. DOI: 10.5753/sibgrapi.est.2024.31638
4| Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. ICLR 2021. URL: https://arxiv.org/pdf/2010.11929
5| Gangwar, A., Gonzalez-Castro, V., Alegre, E., Fidalgo, E. (2021). Attm-cnn: Attention and metric learning based cnn for pornography, age and child sexual abuse (csa) detection in images. Neurocomputing 445, 81–104. DOI: 10.1016/j.neucom.2021.02.056
6| Gangwar, A., Gonzalez-Castro, V., Alegre, E., Fidalgo, E. (2023). Triple-biggan: Semi-supervised generative adversarial networks for image synthesis and classification on sexual facial expression recognition. Neurocomputing 528, 200–216. DOI: 10.1016/j.neucom.2023.01.027
7| Gangwar, A., Gonzalez-Castro, V., Alegre, E., Fidalgo, E., Martínez-Mendoza, A. (2024). Deephsar: Semi-supervised fine-grained learning for multi-label human sexual activity recognition. Information Processing and Management 61. DOI: 10.1016/j.ipm.2024.103800
8| Kaewkorn, H., Zhou, L., Li, W. (2025). Rp-net: A robust polar transformation network for rotation-invariant face detection. Pattern Recognition 158. DOI: 10.1016/J.PATCOG.2024.111044
9| Lee, H.-E., Ermakova, T., Ververis, V., Fabian, B. (2020). Detecting child sexual abuse material: A comprehensive survey. Forensic Science International: Digital Investigation 34, 301022. DOI: 10.1016/j.fsidi.2020.301022
10| Lin, C., Gou, J., Fan, Z., Liao, Y. (2024). A feature fusion-based resnet using the pooling pyramid for age estimation. Proceedings of the International Joint Conference on Neural Networks. DOI: 10.1109/IJCNN60899.2024.10650545
11| Liu, X., Qiu, M., Zhang, Z., Shi, Y., Li, Z., Chen, X., Liu, Y., Chen, X., Yu, H. (2025). Enhancing facial age estimation with local and global multi-attention mechanisms. Pattern Recognition Letters 189, 71–77. DOI: 10.1016/J.PATREC.2025.01.005
12| Morais, P. (2025). Aprendizaje profundo en la clasificación automatizada de imágenes en la detección de abusos sexuales a menores. (unpublished)
13| Moreira, D., Avila, S., Perez, M., Moraes, D., Testoni, V., Valle, E., Goldenstein, S., Rocha, A. (2016). Pornography classification: The hidden clues in video space–time. Forensic Science International 268, 46–61. DOI: 10.1016/J.FORSCIINT.2016.09.010
14| Pereira, M., Dodhia, R., Anderson, H., Brown, R. (2020). Metadata-based detection of child sexual abuse material. arXiv preprint arXiv:2010.02387.
15| Qin, L., Wang, M., Deng, C., Wang, K., Chen, X., Hu, J., Deng, W. (2023). Swinface: A multi-task transformer for face recognition, expression recognition, age estimation and attribute estimation. IEEE Transactions on Circuits and Systems for Video Technology 34, 2223–2234. DOI: 10.1109/TCSVT.2023.3304724
16| Rautela, K., Sharma, D., Kumar, V., Kumar, D. (2024). Obscenity detection transformer for detecting inappropriate contents from videos. Multimedia Tools and Applications 83, 10799–10814. DOI: 10.1007/s11042-023-16078-2
17| Shou, Y., Cao, X., Liu, H., Meng, D. (2025). Masked contrastive graph representation learning for age estimation. Pattern Recognition 158. DOI: 10.1016/J.PATCOG.2024.110974
18| Steinebach, M. (2023). An analysis of PhotoDNA. Proceedings of the 18th International Conference on Availability, Reliability and Security (ARES 2023). ACM. DOI: 10.1145/3600160.3605048
19| Tian, Y., Ye, Q., Doermann, D. (2025). Yolov12: Attention-centric real-time object detectors. URL: https://arxiv.org/abs/2502.12524
20| UNICEF (2026). Artificial intelligence and child sexual abuse and exploitation. URL: https://www.unicef.org/reports/artificial-intelligence-and-child-sexual-abuse-and-exploitation
21| Westlake, B., Brewer, R., Swearingen, T., Ross, A., Patterson, S., Michalski, D., Hole, M., Logos, K., Frank, R., Bright, D., et al. (2022). Developing automated methods to detect and match face and voice biometrics in child sexual abuse videos. Trends and issues in crime and criminal justice (648), 1–15.
22| Yang, J. (2025). Facial recognition optimization based on adversarial sample generation in the field of artificial intelligence. Discover Artificial Intelligence 5. DOI: 10.1007/S44163-025-00287-9
23| Yu, S., Zhao, Q. (2025). Improving age estimation in occluded facial images with knowledge distillation and layer-wise feature reconstruction. Applied Sciences (Switzerland) 15. DOI: 10.3390/APP15115806
24| Yu, W., Zhou, P., Yan, S., Wang, X. (2025). Inceptionnext: When inception meets convnext. URL: https://arxiv.org/abs/2303.16900
25| Zhang, J., Hu, N. (2025). Accuracy and robustness evaluation of deep learning algorithms in facial recognition systems. Systems and Soft Computing 7. DOI: 10.1016/J.SASC.2025.200252
26| Zhu, D., Shan, X., Wu, C., Yung, K., Ip, A. (2024). Multi frame obscene video detection with vit: An effective for detecting inappropriate content. International Journal on Semantic Web and Information Systems 20. DOI: 10.4018/IJSWIS.359768
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Pablo Morais, Eduardo Fidalgo, Víctor González-Castro, Waqar Tanveer, Milad Mirjalili, Enrique Alegre
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
