# Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets

arXiv: https://arxiv.org/abs/2204.14110 · HTML: https://mlsanity.com/paper/2204.14110/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 58 references that are in the map.
- First posted on arXiv 29 Apr 2022.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [Diversity in Faces](https://mlsanity.com/paper/1901.10436/) (2019)
- [Measuring Model Biases in the Absence of Ground Truth](https://mlsanity.com/paper/2103.03417/) (2021)
- [Reusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards](https://mlsanity.com/paper/2108.07374/) (2021)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Evaluating Performance of an Adult Pornography Classifier for Child Sexual Abuse Detection](https://mlsanity.com/paper/2005.08766/) (2020)

## Built on by (most cited first, 10 of 10)

- [Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets](https://mlsanity.com/paper/2305.09072/) (2023)
- [Neglected Risks: The Disturbing Reality of Children's Images in Datasets and the Urgent Call for Accountability](https://mlsanity.com/paper/2504.14446/) (2025)
- [Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery](https://mlsanity.com/paper/2403.01183/) (2024)
- [Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models](https://mlsanity.com/paper/2505.06621/) (2025)
- [A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild](https://mlsanity.com/paper/2506.10117/) (2025)
- [VModA: An Effective Framework for Adaptive NSFW Image Moderation](https://mlsanity.com/paper/2505.23386/) (2025)
- [An Efficient Hybrid Deep Learning Approach for Detecting Online Abusive Language](https://mlsanity.com/paper/2603.09984/) (2026)
- [CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research](https://mlsanity.com/paper/2604.07132/) (2026)
- [Classifying by Proxy: Explainable and Reproducible Ensemble of Proxy Tasks for Child Sexual Abuse Imagery Classification](https://mlsanity.com/paper/2606.15993/) (2026)
- [Detecting CSAM Text-to-Image LoRAs From Weights](https://mlsanity.com/paper/2607.25750/) (2026)

## Abstract (arXiv)

The online sharing and viewing of Child Sexual Abuse Material (CSAM) are growing fast, such that human experts can no longer handle the manual inspection. However, the automatic classification of CSAM is a challenging field of research, largely due to the inaccessibility of target data that is - and should forever be - private and in sole possession of law enforcement agencies. To aid researchers in drawing insights from unseen data and safely providing further understanding of CSAM images, we propose an analysis template that goes beyond the statistics of the dataset and respective labels. It focuses on the extraction of automatic signals, provided both by pre-trained machine learning models, e.g., object categories and pornography detection, as well as image metrics such as luminance and sharpness. Only aggregated statistics of sparse signals are provided to guarantee the anonymity of children and adolescents victimized. The pipeline allows filtering the data by applying thresholds to each specified signal and provides the distribution of such signals within the subset, correlations between signals, as well as a bias evaluation. We demonstrated our proposal on the Region-based annotated Child Pornography Dataset (RCPD), one of the few CSAM benchmarks in the literature, composed of over 2000 samples among regular and CSAM images, produced in partnership with Brazil's Federal Police. Although noisy and limited in several senses, we argue that automatic signals can highlight important aspects of the overall distribution of data, which is valuable for databases that can not be disclosed. Our goal is to safely publicize the characteristics of CSAM datasets, encouraging researchers to join the field and perhaps other institutions to provide similar reports on their benchmarks.