High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking

2026-03-25

AI Summary

This work addresses the critical threat posed by deepfake facial content to media provenance, integrity, and copyright protection, as existing watermarking methods struggle to simultaneously achieve precise localization, visual fidelity, and content recoverability. To this end, we propose VeriFi, a novel framework that embeds watermarks in a compact semantic latent space, enabling pixel-level tampering localization, high-fidelity face recovery, and robust copyright verification. Our approach innovatively leverages latent-space watermarks as content priors, facilitating fine-grained manipulation detection without explicit localization signals. Furthermore, we design an AIGC attack simulator based on latent-space mixing and seamless blending to enhance robustness against real-world forgery pipelines. Experiments on CelebA-HQ and FFHQ demonstrate that VeriFi significantly outperforms state-of-the-art methods in watermark robustness, localization accuracy, and reconstruction quality.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Data transparency and provenance

Abstract

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.

Problem

• deepfakes
• face manipulation
• content recovery
• digital watermarking
• media forensics

Innovation

• versatile watermarking
• content recovery
• semantic latent watermark
• manipulation localization
• AIGC attack simulation