Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
This addresses privacy concerns for individuals in applications like smart cameras and home robots, offering a novel approach to reversible anonymization.
The paper tackles the problem of privacy-sensitive face identity in visual data by proposing a face identity transformer that enables password-based anonymization and deanonymization, achieving photo-realistic results without sacrificing privacy compared to existing methods.
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.