Secure reversible privacy protection for face multiple attribute editing

The demand for face attribute editing is increasing across various applications, such as digital media and virtual reality. However, while existing methods can achieve high-quality multi-attribute editing, they often struggle to balance privacy protection and image reversibility, and are prone to causing undesired changes in non-target attributes. To address these issues, we propose a novel Multi-Layer Mapping and Password Fusion (M-LMPF) framework for efficient and flexible face attribute editing with reversible privacy protection. Our approach integrates multi-attribute editing with secure reversible image attribute protection, enabling precise control over the modification of target attributes while preserving facial identity consistency and avoiding changes to other attributes. The framework employs a deep multi-layer latent mapping network that embeds password information at different granular levels in the latent space, allowing for fine-grained control over facial features. Additionally, we introduce a new encryption and decryption mechanism to ensure reversible editing of specific attributes, effectively preventing unauthorized access. Extensive experiments demonstrate that the M-LMPF framework outperforms state-of-the-art methods in attribute editing accuracy, reversibility, identity consistency, and image quality.