# Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models

arXiv: https://arxiv.org/abs/2505.06621 · HTML: https://mlsanity.com/paper/2505.06621/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 69 references that are in the map.
- First posted on arXiv 10 May 2025.

## Builds on (most cited first, 21 of 21)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research](https://mlsanity.com/paper/2112.01716/) (2021)
- [DataPerf: Benchmarks for Data-Centric AI Development](https://mlsanity.com/paper/2207.10062/) (2022)
- [Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash](https://mlsanity.com/paper/2111.06628/) (2021)
- [What can Data-Centric AI Learn from Data and ML Engineering?](https://mlsanity.com/paper/2112.06439/) (2021)
- [Attribute Privacy: Framework and Mechanisms](https://mlsanity.com/paper/2009.04013/) (2020)
- [Sparse Spatial Transformers for Few-Shot Learning](https://mlsanity.com/paper/2109.12932/) (2021)
- [Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets](https://mlsanity.com/paper/2204.14110/) (2022)
- [FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition](https://mlsanity.com/paper/1907.07570/) (2019)
- [Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery](https://mlsanity.com/paper/2403.01183/) (2024)
- [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, 4 of 4)

- [Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification](https://mlsanity.com/paper/2509.26457/) (2025)
- [CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research](https://mlsanity.com/paper/2604.07132/) (2026)
- [Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data](https://mlsanity.com/paper/2605.29230/) (2026)
- [Classifying by Proxy: Explainable and Reproducible Ensemble of Proxy Tasks for Child Sexual Abuse Imagery Classification](https://mlsanity.com/paper/2606.15993/) (2026)

## Abstract (arXiv)

The distribution of child sexual abuse imagery (CSAI) is an ever-growing concern of our modern world; children who suffered from this heinous crime are revictimized, and the growing amount of illegal imagery distributed overwhelms law enforcement agents (LEAs) with the manual labor of categorization. To ease this burden researchers have explored methods for automating data triage and detection of CSAI, but the sensitive nature of the data imposes restricted access and minimal interaction between real data and learning algorithms, avoiding leaks at all costs. In observing how these restrictions have shaped the literature we formalize a definition of "Proxy Tasks", i.e., the substitute tasks used for training models for CSAI without making use of CSA data. Under this new terminology we review current literature and present a protocol for making conscious use of Proxy Tasks together with consistent input from LEAs to design better automation in this field. Finally, we apply this protocol to study -- for the first time -- the task of Few-shot Indoor Scene Classification on CSAI, showing a final model that achieves promising results on a real-world CSAI dataset whilst having no weights actually trained on sensitive data.