Face Deidentification with Generative Deep Neural Networks

TL;DR

This paper introduces a novel face deidentification method using generative neural networks to create artificial faces, effectively anonymizing individuals while preserving data utility for non-identity-related applications.

Contribution

The paper presents a new pipeline employing generative neural networks for face deidentification, ensuring privacy and data usability, which surpasses traditional blurring techniques.

Findings

Recognition performance on deidentified images is near chance level.

Generated faces effectively anonymize subjects in images and videos.

The approach maintains non-identity data characteristics.

Abstract

Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods 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 work we 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. To demonstrate the feasibility of our approach, we perform experiments using automated recognition tools and human annotators. Our results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is highly effective.