LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
This addresses the problem of deepfake detection for privacy and security, offering a novel proactive approach that is incremental in improving generalizability over passive methods.
The paper tackles the challenge of detecting hyper-realistic deepfake facial images by proposing LampMark, a proactive detection method using training-free landmark perceptual watermarks, achieving superior performance in watermark recovery and detection compared to state-of-the-art methods across various scenarios.
Deepfake facial manipulation has garnered significant public attention due to its impacts on enhancing human experiences and posing privacy threats. Despite numerous passive algorithms that have been attempted to thwart malicious Deepfake attacks, they mostly struggle with the generalizability challenge when confronted with hyper-realistic synthetic facial images. To tackle the problem, this paper proposes a proactive Deepfake detection approach by introducing a novel training-free landmark perceptual watermark, LampMark for short. We first analyze the structure-sensitive characteristics of Deepfake manipulations and devise a secure and confidential transformation pipeline from the structural representations, i.e. facial landmarks, to binary landmark perceptual watermarks. Subsequently, we present an end-to-end watermarking framework that imperceptibly and robustly embeds and extracts watermarks concerning the images to be protected. Relying on promising watermark recovery accuracies, Deepfake detection is accomplished by assessing the consistency between the content-matched landmark perceptual watermark and the robustly recovered watermark of the suspect image. Experimental results demonstrate the superior performance of our approach in watermark recovery and Deepfake detection compared to state-of-the-art methods across in-dataset, cross-dataset, and cross-manipulation scenarios.