Facial privacy in the digital era: A comprehensive survey on methods, evaluation, and future directions

Abstract

With the advancement of computer vision technology and smart devices, images and videos containing facial information are increasingly shared on social media, making it easier for facial data to be collected and misused. As sensitive biometric data, once facial information is leaked, it may cause irreversible damage to personal privacy. Ensuring the security of facial information while benefiting from technological conveniences has become a critical research area. Many surveys have summarized existing protection measures, which often focus on specific issues or are oriented toward particular technologies, so existing methods have not been comprehensively summarized. In this paper, we categorize facial privacy-preserving methods into four paradigms: appearance-guided, identity-guided, reversible, and privacy-preserving for facial recognition systems. We offer an in-depth review of the most representative methods, emphasizing their advantages and functional characteristics. Additionally, we present commonly used datasets and evaluation metrics and analyze the performance of current methods. Finally, we discuss the challenges and opportunities for practical applications in facial privacy protection, offering insights for future research.