# Human-interpretable and deep features for image privacy classification

arXiv: https://arxiv.org/abs/2310.19582 · HTML: https://mlsanity.com/paper/2310.19582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 5 of 5)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Places: An Image Database for Deep Scene Understanding](https://mlsanity.com/paper/1610.02055/) (2016)
- [Image Privacy Prediction Using Deep Neural Networks](https://mlsanity.com/paper/1903.03695/) (2019)
- [Content-based Graph Privacy Advisor](https://mlsanity.com/paper/2210.11169/) (2022)

## Built on by (most cited first, 4 of 4)

- [Image-guided topic modeling for interpretable privacy classification](https://mlsanity.com/paper/2409.18674/) (2024)
- [Explaining models relating objects and privacy](https://mlsanity.com/paper/2405.01646/) (2024)
- [The impact of abstract and object tags on image privacy classification](https://mlsanity.com/paper/2510.07976/) (2025)
- [PrivLEX: Detecting legal concepts in images through Vision-Language Models](https://mlsanity.com/paper/2601.09449/) (2026)

## Abstract (arXiv)

Privacy is a complex, subjective and contextual concept that is difficult to define. Therefore, the annotation of images to train privacy classifiers is a challenging task. In this paper, we analyse privacy classification datasets and the properties of controversial images that are annotated with contrasting privacy labels by different assessors. We discuss suitable features for image privacy classification and propose eight privacy-specific and human-interpretable features. These features increase the performance of deep learning models and, on their own, improve the image representation for privacy classification compared with much higher dimensional deep features.