Synth-Tracker: Recoverable and Traceable Defense Watermark against Face Synthesis

The fast development of face synthesis technology has brought an increasing number of face synthesis services. However, when such services are misused in malicious activities, the face synthesis service providers (FSSPs) may face serious legal risks. Therefore, this paper proposes a recoverable and traceable defense watermarking method to protect FSSPs. The method designs a decoupled data hiding framework to separate two embedding tasks, where the source image and operator's ID are inserted into the synthesized image respectively by invertible neural network and convolutional neural network. Furthermore, a facial masking strategy is employed to exclude background information of source image for enhancing the imperceptibility. The proposed method enables forensic traceability for the FSSPs to track back to the malicious users and recover the original source images, building a chain of evidence and inferring the forger's intent after forgery. Experimental results show that compared to the existing methods, the proposed method has superior performance in source image recovery and ID extraction. In addition, the plug-and-play design of the proposed method allows for seamless integration into current face synthesis services. The code is available at https://github.com/imagecbj/ Active-Defense-for-Face-Synthesis.