RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
This addresses privacy concerns for individuals in applications like video anonymization, though it is incremental as it builds upon pre-existing StyleGAN2 technology.
The paper tackles the problem of protecting facial identity from misuse by proposing RiDDLE, a method for reversible and diversified de-identification using a latent encryptor, which achieves better quality, higher diversity, and stronger reversibility compared to existing alternatives.
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.