Password-conditioned Anonymization and Deanonymization with Face Identity Transformers

Abstract

Cameras are prevalent in our daily lives, and enable many useful systems built upon computer vision technologies such as smart cameras and home robots for service applications. However, there is also an increasing societal concern as the captured images/videos may contain privacy-sensitive information (e.g., face identity). We propose a novel face identity transformer which enables automated photo-realistic password-based anonymization as well as deanonymization of human faces appearing in visual data. Our face identity transformer is trained to (1) remove face identity information after anonymization, (2) make the recovery of the original face possible when given the correct password, and (3) return a wrong--but photo-realistic--face given a wrong password. Extensive experiments show that our approach enables multimodal password-conditioned face anonymizations and deanonymizations, without sacrificing privacy compared to existing anonymization approaches.

arXiv commentECCV 2020

References in corpus (8)

• Conditional Generative Adversarial Nets
• Deep Learning with Differential Privacy
• Generative Adversarial Text to Image Synthesis
• Learning Face Representation from Scratch
• Toward Multimodal Image-to-Image Translation
• Invertible Conditional GANs for image editing
• Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
• Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning