Predavanje: Face deidentification with generative deep networks

Sažetak predavanja

Face deidentification is an active topic among privacy and security researchers. Early deidentification techniques relying on image blurring or pixelization were replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and at the same time aim at retaining certain characteristics of the data even after deidentification. The latter aspect is particularly important, as it allows to exploit the deidentified data in applications for which identity information is irrelevant. In this talk we will present a novel face deidentification pipeline, which ensures anonymity by synthesizing artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or video, while preserving non-identity-related aspects of the data and consequently enabling data utilization. Since generative networks are very adaptive and can utilize a diverse set of 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. Additional examples of deidentification techniques using GNNs will also be discussed.

O predavaču

Vitomir Štruc is an Associate Professor at the Faculty of Electrical Engineering at the University of Ljubljana Slovenia. He received his PhD degree in electrical engineering from the University of Ljubljana in 2010, for which he was awarded the Vodovnik award. He is also the recipient of the “2015 young researcher award” of the University of Ljubljana. Vitomir participated as a key member in numerous national and EU funded R&D projects and authored (or co-authored) more than 100 research papers for leading international journals and conferences related to different areas of computer vision, image processing, pattern recognition, and biometrics. Vitomir served on the organizing committees of several workshops and conferences and is currently a workshop & tutorial co-chair for IEEE FG 2017, a competition co-chair for IEEE/IAPR IJCB 2017, a program co-chair for ISPA 2017 and co-organizer of the 2017 Biometrics in the Wild workshop (BWild 2017). Vitomir is a member of the editorial board of IET Biometrics and serves as a guest editor for the Image and Vision Computing special issue on “Biometrics in the Wild”. He is a member of the IEEE, IAPR, the national contact point for the EAB and the current president of the Slovenian Pattern Recognition Society.