# Anonymizing k-Facial Attributes via Adversarial Perturbations

arXiv: https://arxiv.org/abs/1805.09380 · HTML: https://mlsanity.com/paper/1805.09380/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 8 of 8)

- [Adventures of Trustworthy Vision-Language Models: A Survey](https://mlsanity.com/paper/2312.04231/) (2023)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms](https://mlsanity.com/paper/2310.15848/) (2023)
- [On Mask-based Image Set Desensitization with Recognition Support](https://mlsanity.com/paper/2312.08975/) (2023)
- [A Key-Driven Framework for Identity-Preserving Face Anonymization](https://mlsanity.com/paper/2409.03434/) (2024)
- [PrivacyProber: Assessment and Detection of Soft-Biometric Privacy-Enhancing Techniques](https://mlsanity.com/paper/2211.08864/) (2022)
- [CausalVE: Face Video Privacy Encryption via Causal Video Prediction](https://mlsanity.com/paper/2409.19306/) (2024)
- [Face anonymization preserving facial expressions and photometric realism](https://mlsanity.com/paper/2603.17567/) (2026)

## Abstract (arXiv)

A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age. Advancements in machine learning algorithms and popularity of sharing images on the World Wide Web, including social media websites, have increased the scope of data analytics and information profiling from photo collections. This poses a serious privacy threat for individuals who do not want to be profiled. This research presents a novel algorithm for anonymizing selective attributes which an individual does not want to share without affecting the visual quality of images. Using the proposed algorithm, a user can select single or multiple attributes to be surpassed while preserving identity information and visual content. The proposed adversarial perturbation based algorithm embeds imperceptible noise in an image such that attribute prediction algorithm for the selected attribute yields incorrect classification result, thereby preserving the information according to user's choice. Experiments on three popular databases i.e. MUCT, LFWcrop, and CelebA show that the proposed algorithm not only anonymizes k-attributes, but also preserves image quality and identity information.