# Image Privacy Prediction Using Deep Neural Networks

arXiv: https://arxiv.org/abs/1903.03695 · HTML: https://mlsanity.com/paper/1903.03695/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2019.

## Built on by (most cited first, 13 of 13)

- [Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks](https://mlsanity.com/paper/2204.12050/) (2022)
- [Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Dataset](https://mlsanity.com/paper/2507.13981/) (2025)
- [Human-interpretable and deep features for image privacy classification](https://mlsanity.com/paper/2310.19582/) (2023)
- [Image-guided topic modeling for interpretable privacy classification](https://mlsanity.com/paper/2409.18674/) (2024)
- [Uncertainty-aware Personal Assistant for Making Personalized Privacy Decisions](https://mlsanity.com/paper/2205.06544/) (2022)
- [PEAK: Explainable Privacy Assistant through Automated Knowledge Extraction](https://mlsanity.com/paper/2301.02079/) (2023)
- [Learning Privacy from Visual Entities](https://mlsanity.com/paper/2503.12464/) (2025)
- [Proposing an Interactive Audit Pipeline for Visual Privacy Research](https://mlsanity.com/paper/2111.03984/) (2021)
- [Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning](https://mlsanity.com/paper/2406.12736/) (2024)
- [On the Robustness of Vision-Language Models in Zero-shot Privacy Classification](https://mlsanity.com/paper/2510.09253/) (2025)
- [Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications](https://mlsanity.com/paper/2110.01676/) (2021)
- [The impact of abstract and object tags on image privacy classification](https://mlsanity.com/paper/2510.07976/) (2025)
- [Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds](https://mlsanity.com/paper/2602.07149/) (2026)

## Abstract (arXiv)

Images today are increasingly shared online on social networking sites such as Facebook, Flickr, Foursquare, and Instagram. Despite that current social networking sites allow users to change their privacy preferences, this is often a cumbersome task for the vast majority of users on the Web, who face difficulties in assigning and managing privacy settings. Thus, automatically predicting images' privacy to warn users about private or sensitive content before uploading these images on social networking sites has become a necessity in our current interconnected world. In this paper, we explore learning models to automatically predict appropriate images' privacy as private or public using carefully identified image-specific features. We study deep visual semantic features that are derived from various layers of Convolutional Neural Networks (CNNs) as well as textual features such as user tags and deep tags generated from deep CNNs. Particularly, we extract deep (visual and tag) features from four pre-trained CNN architectures for object recognition, i.e., AlexNet, GoogLeNet, VGG-16, and ResNet, and compare their performance for image privacy prediction. Results of our experiments on a Flickr dataset of over thirty thousand images show that the learning models trained on features extracted from ResNet outperform the state-of-the-art models for image privacy prediction. We further investigate the combination of user tags and deep tags derived from CNN architectures using two settings: (1) SVM on the bag-of-tags features; and (2) text-based CNN. Our results show that even though the models trained on the visual features perform better than those trained on the tag features, the combination of deep visual features with image tags shows improvements in performance over the individual feature sets.