TapFace: A task-oriented facial privacy protection framework

Abstract

Deep learning has been widely employed in various face recognition and analysis tasks, highlighting the importance of facial privacy protection. Numerous facial de-identification methods have been proposed to maximize image utility and prevent disclosing private information. However, existing methods encounter various challenges due to the diversity in the definitions of facial privacy. Thus, these methods fail to adaptively cater to varying facial privacy protection requirements. Therefore, this paper introduces TapFace, a task-oriented facial privacy protection framework, that enables users to tailor task, privacy, and background attributes according to specific task demands. Specifically, the TapFace framework processes original images through image-guided generation and privacy attribute randomization, ensuring the preservation of task-relevant features while effectively anonymizing private information. The experimental results from multiple real-world datasets indicate that the proposed framework can adaptively protect facial privacy while fulfilling the images’ usability requirements during specific tasks.