Detecting sexually explicit content in the context of the child sexual abuse materials (CSAM): end-to-end classifiers and region-based networks
This addresses the need for automated content moderation to reduce human exposure to harmful images and speed up detection for law enforcement and tech companies, though it is incremental in applying existing methods to a sensitive domain.
The study tackled the problem of automatically detecting sexually explicit content to aid in identifying child sexual abuse materials, achieving 90.17% accuracy with an end-to-end classifier after data augmentation.
Child sexual abuse materials (CSAM) pose a significant threat to the safety and well-being of children worldwide. Detecting and preventing the distribution of such materials is a critical task for law enforcement agencies and technology companies. As content moderation is often manual, developing an automated detection system can help reduce human reviewers' exposure to potentially harmful images and accelerate the process of counteracting. This study presents methods for classifying sexually explicit content, which plays a crucial role in the automated CSAM detection system. Several approaches are explored to solve the task: an end-to-end classifier, a classifier with person detection and a private body parts detector. All proposed methods are tested on the images obtained from the online tool for reporting illicit content. Due to legal constraints, access to the data is limited, and all algorithms are executed remotely on the isolated server. The end-to-end classifier yields the most promising results, with an accuracy of 90.17%, after augmenting the training set with the additional neutral samples and adult pornography. While detection-based methods may not achieve higher accuracy rates and cannot serve as a final classifier on their own, their inclusion in the system can be beneficial. Human body-oriented approaches generate results that are easier to interpret, and obtaining more interpretable results is essential when analyzing models that are trained without direct access to data.