# PrivacyProber: Assessment and Detection of Soft-Biometric Privacy-Enhancing Techniques

arXiv: https://arxiv.org/abs/2211.08864 · HTML: https://mlsanity.com/paper/2211.08864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 71 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 30 of 32)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](https://mlsanity.com/paper/1603.01249/) (2016)
- [Image Inpainting via Generative Multi-column Convolutional Neural Networks](https://mlsanity.com/paper/1810.08771/) (2018)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [Trustworthy AI](https://mlsanity.com/paper/2011.02272/) (2020)
- [AdvDrop: Adversarial Attack to DNNs by Dropping Information](https://mlsanity.com/paper/2108.09034/) (2021)
- [PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy](https://mlsanity.com/paper/2001.00561/) (2020)
- [Face hallucination using cascaded super-resolution and identity priors](https://mlsanity.com/paper/1805.10938/) (2018)
- [Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification](https://mlsanity.com/paper/2002.03683/) (2020)
- [Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images](https://mlsanity.com/paper/1712.00321/) (2017)
- [Face Recognition in Low Quality Images: A Survey](https://mlsanity.com/paper/1805.11519/) (2018)
- [An Overview of Privacy-enhancing Technologies in Biometric Recognition](https://mlsanity.com/paper/2206.10465/) (2022)
- [A Survey of Machine Learning Techniques in Adversarial Image Forensics](https://mlsanity.com/paper/2010.09680/) (2020)
- [How are attributes expressed in face DCNNs?](https://mlsanity.com/paper/1910.05657/) (2019)
- [EMOPAIN Challenge 2020: Multimodal Pain Evaluation from Facial and Bodily Expressions](https://mlsanity.com/paper/2001.07739/) (2020)
- [Fawkes: Protecting Privacy against Unauthorized Deep Learning Models](https://mlsanity.com/paper/2002.08327/) (2020)
- [Adversarial Defense based on Structure-to-Signal Autoencoders](https://mlsanity.com/paper/1803.07994/) (2018)
- [Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers](https://mlsanity.com/paper/1807.11936/) (2018)
- [Face Deidentification with Generative Deep Neural Networks](https://mlsanity.com/paper/1707.09376/) (2017)
- [Facial Attributes: Accuracy and Adversarial Robustness](https://mlsanity.com/paper/1801.02480/) (2018)
- [Anonymizing k-Facial Attributes via Adversarial Perturbations](https://mlsanity.com/paper/1805.09380/) (2018)
- [Face Hallucination Revisited: An Exploratory Study on Dataset Bias](https://mlsanity.com/paper/1812.09010/) (2018)

## Abstract (arXiv)

Soft-biometric privacy-enhancing techniques represent machine learning methods that aim to: (i) mitigate privacy concerns associated with face recognition technology by suppressing selected soft-biometric attributes in facial images (e.g., gender, age, ethnicity) and (ii) make unsolicited extraction of sensitive personal information infeasible. Because such techniques are increasingly used in real-world applications, it is imperative to understand to what extent the privacy enhancement can be inverted and how much attribute information can be recovered from privacy-enhanced images. While these aspects are critical, they have not been investigated in the literature. We, therefore, study the robustness of several state-of-the-art soft-biometric privacy-enhancing techniques to attribute recovery attempts. We propose PrivacyProber, a high-level framework for restoring soft-biometric information from privacy-enhanced facial images, and apply it for attribute recovery in comprehensive experiments on three public face datasets, i.e., LFW, MUCT and Adience. Our experiments show that the proposed framework is able to restore a considerable amount of suppressed information, regardless of the privacy-enhancing technique used, but also that there are significant differences between the considered privacy models. These results point to the need for novel mechanisms that can improve the robustness of existing privacy-enhancing techniques and secure them against potential adversaries trying to restore suppressed information.