High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
This addresses the threat of deepfakes for media forensics and copyright protection, offering a practical defense with incremental improvements over prior watermarking methods.
The paper tackles the problem of media integrity and copyright protection against AIGC-driven face manipulation by proposing VeriFi, a versatile watermarking framework that achieves high-fidelity face content recovery and fine-grained localization, outperforming baselines in robustness, accuracy, and recovery quality on datasets like CelebA-HQ and FFHQ.
The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Prior versatile watermarking systems typically rely on embedding explicit localization payloads, which introduces a fidelity--functionality trade-off: larger localization signals degrade visual quality and often reduce decoding robustness under strong generative edits. Moreover, existing methods rarely support content recovery, limiting their forensic value when original evidence must be reconstructed. To address these challenges, we present VeriFi, a versatile watermarking framework that unifies copyright protection, pixel-level manipulation localization, and high-fidelity face content recovery. VeriFi makes three key contributions: (1) it embeds a compact semantic latent watermark that serves as an content-preserving prior, enabling faithful restoration even after severe manipulations; (2) it achieves fine-grained localization without embedding localization-specific artifacts by correlating image features with decoded provenance signals; and (3) it introduces an AIGC attack simulator that combines latent-space mixing with seamless blending to improve robustness to realistic deepfake pipelines. Extensive experiments on CelebA-HQ and FFHQ show that VeriFi consistently outperforms strong baselines in watermark robustness, localization accuracy, and recovery quality, providing a practical and verifiable defense for deepfake forensics.