TU Darmstadt / ULB / TUbiblio

Unsupervised privacy-enhancement of face representations using similarity-sensitive noise transformations

Terhörst, Philipp and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan (2019):
Unsupervised privacy-enhancement of face representations using similarity-sensitive noise transformations.
In: Applied Intelligence, Springer, pp. 3043-3060, 49, (8), ISSN 0924-669X,
DOI: 10.1007/s10489-019-01432-5,
[Online-Edition: https://doi.org/10.1007/s10489-019-01432-5],
[Article]

Abstract

Face images processed by a biometric system are expected to be used for recognition purposes only. However, recent work presented possibilities for automatically deducing additional information about an individual from their face data. By using soft-biometric estimators, information about gender, age, ethnicity, sexual orientation or the health state of a person can be obtained. This raises a major privacy issue. Previous works presented supervised solutions that require large amount of private data in order to suppress a single attribute. In this work, we propose a privacy-preserving solution that does not require these sensitive information and thus, works in an unsupervised manner. Further, our approach offers privacy protection that is not limited to a single known binary attribute or classifier. We do that by proposing similarity-sensitive noise transformations and investigate their effect and the effect of dimensionality reduction methods on the task of privacy preservation. Experiments are done on a publicly available database and contain analyses of the recognition performance, as well as investigations of the estimation performance of the binary attribute of gender and the continuous attribute of age. We further investigated the estimation performance of these attributes when the prior knowledge about the used privacy mechanism is explicitly utilized. The results show that using this information leads to significantly enhancement of the estimation quality. Finally, we proposed a metric to evaluate the trade-off between the privacy gain and the recognition loss for privacy-preservation techniques. Our experiments showed that the proposed cosine-sensitive noise transformation was successful in reducing the possibility of estimating the soft private information in the data, while having significantly smaller effect on the intended recognition performance.

Item Type: Article
Erschienen: 2019
Creators: Terhörst, Philipp and Damer, Naser and Kirchbuchner, Florian and Kuijper, Arjan
Title: Unsupervised privacy-enhancement of face representations using similarity-sensitive noise transformations
Language: English
Abstract:

Face images processed by a biometric system are expected to be used for recognition purposes only. However, recent work presented possibilities for automatically deducing additional information about an individual from their face data. By using soft-biometric estimators, information about gender, age, ethnicity, sexual orientation or the health state of a person can be obtained. This raises a major privacy issue. Previous works presented supervised solutions that require large amount of private data in order to suppress a single attribute. In this work, we propose a privacy-preserving solution that does not require these sensitive information and thus, works in an unsupervised manner. Further, our approach offers privacy protection that is not limited to a single known binary attribute or classifier. We do that by proposing similarity-sensitive noise transformations and investigate their effect and the effect of dimensionality reduction methods on the task of privacy preservation. Experiments are done on a publicly available database and contain analyses of the recognition performance, as well as investigations of the estimation performance of the binary attribute of gender and the continuous attribute of age. We further investigated the estimation performance of these attributes when the prior knowledge about the used privacy mechanism is explicitly utilized. The results show that using this information leads to significantly enhancement of the estimation quality. Finally, we proposed a metric to evaluate the trade-off between the privacy gain and the recognition loss for privacy-preservation techniques. Our experiments showed that the proposed cosine-sensitive noise transformation was successful in reducing the possibility of estimating the soft private information in the data, while having significantly smaller effect on the intended recognition performance.

Journal or Publication Title: Applied Intelligence
Volume: 49
Number: 8
Publisher: Springer
Uncontrolled Keywords: Biometrics, Privacy enhancing technologies, Privacy protection, Face recognition
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 10 Jul 2019 11:20
DOI: 10.1007/s10489-019-01432-5
Official URL: https://doi.org/10.1007/s10489-019-01432-5
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item