Face deidentification with generative deep neural networks

Blaž Meden*, Refik Can Malli, Sebastjan Fabijan, Hazim Kemal Ekenel, Vitomir Štruc, Peter Peer

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

51 Citations (Scopus)


Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelisation have been replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and retain certain characteristics of the data even after deidentification. The latter aspect is important, as it allows the deidentified data to be used in applications for which identity information is irrelevant. In this work, the authors present a novel face deidentification pipeline, which ensures anonymity by synthesising artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or videos, while preserving non-identity-related aspects of the data and consequently enabling data utilisation. Since generative networks are highly adaptive and can utilise diverse parameters (pertaining to the appearance of the generated output in terms of facial expressions, gender, race etc.), they represent a natural choice for the problem of face deidentification. To demonstrate the feasibility of the authors' approach, they perform experiments using automated recognition tools and human annotators. Their results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is effective.

Original languageEnglish
Pages (from-to)1046-1054
Number of pages9
JournalIET Signal Processing
Issue number9
Publication statusPublished - 1 Dec 2017

Bibliographical note

Publisher Copyright:
© The Institution of Engineering and Technology 2017.


Dive into the research topics of 'Face deidentification with generative deep neural networks'. Together they form a unique fingerprint.

Cite this