k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification
Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification technique...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/20/1/60 |
| _version_ | 1828394472673640448 |
|---|---|
| author | Blaž Meden Žiga Emeršič Vitomir Štruc Peter Peer |
| author_facet | Blaž Meden Žiga Emeršič Vitomir Štruc Peter Peer |
| author_sort | Blaž Meden |
| collection | DOAJ |
| description | Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area. |
| first_indexed | 2024-12-10T07:56:04Z |
| format | Article |
| id | doaj.art-6f9ff4649f7946808e634a0f17d0fcf8 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-12-10T07:56:04Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-6f9ff4649f7946808e634a0f17d0fcf82022-12-22T01:56:54ZengMDPI AGEntropy1099-43002018-01-012016010.3390/e20010060e20010060k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face DeidentificationBlaž Meden0Žiga Emeršič1Vitomir Štruc2Peter Peer3Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, SI-1000 Ljubljana, SloveniaFaculty of Computer and Information Science, University of Ljubljana, Večna pot 113, SI-1000 Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, SI-1000 Ljubljana, SloveniaFaculty of Computer and Information Science, University of Ljubljana, Večna pot 113, SI-1000 Ljubljana, SloveniaImage and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.http://www.mdpi.com/1099-4300/20/1/60face deidentificationgenerative neural networksk-Same algorithm |
| spellingShingle | Blaž Meden Žiga Emeršič Vitomir Štruc Peter Peer k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification Entropy face deidentification generative neural networks k-Same algorithm |
| title | k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification |
| title_full | k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification |
| title_fullStr | k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification |
| title_full_unstemmed | k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification |
| title_short | k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification |
| title_sort | k same net k anonymity with generative deep neural networks for face deidentification |
| topic | face deidentification generative neural networks k-Same algorithm |
| url | http://www.mdpi.com/1099-4300/20/1/60 |
| work_keys_str_mv | AT blazmeden ksamenetkanonymitywithgenerativedeepneuralnetworksforfacedeidentification AT zigaemersic ksamenetkanonymitywithgenerativedeepneuralnetworksforfacedeidentification AT vitomirstruc ksamenetkanonymitywithgenerativedeepneuralnetworksforfacedeidentification AT peterpeer ksamenetkanonymitywithgenerativedeepneuralnetworksforfacedeidentification |