This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused. Built upon a pre-learned StyleGAN2 generator, RiDDLE manages to encrypt and decrypt the facial identity within the latent space. The design of RiDDLE has three appealing properties. First, the encryption process is cipher-guided and hence allows diverse anonymization using different passwords. Second, the true identity can only be decrypted with the correct password, otherwise the system will produce another de-identified face to maintain the privacy. Third, both encryption and decryption share an efficient implementation, benefiting from a carefully tailored lightweight encryptor. Comparisons with existing alternatives confirm that our approach accomplishes the de-identification task with better quality, higher diversity, and stronger reversibility. We further demonstrate the effectiveness of RiDDLE in anonymizing videos. Code and models will be made publicly available.

翻译：本文提出RiDDLE（Reversible and Diversified De-identification with Latent Encryptor，基于潜在加密器的可逆与多样化去身份识别），旨在保护人脸身份信息免遭滥用。该方法基于预训练的StyleGAN2生成器，能够在潜在空间中对人脸身份进行加密与解密。RiDDLE的设计具有三个吸引人的特性：第一，加密过程受密码引导，因此可通过不同密码实现多样化的匿名化处理；第二，真实身份仅可通过正确密码解密，否则系统将生成另一张去身份化人脸以保护隐私；第三，加密与解密过程均得益于精心设计的轻量级加密器，从而共享高效实现方案。与现有替代方法的比较证实，本方法在去身份识别任务中实现了更优的质量、更高的多样性及更强的可逆性。我们进一步展示了RiDDLE在视频匿名化中的有效性。相关代码与模型将对外公开。