V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection

TL;DR

V2A-Mark is a versatile deep watermarking method that embeds invisible visual-audio watermarks into videos for precise tampering localization and copyright protection, addressing current limitations in multimedia forensics.

Contribution

It introduces a novel multimodal watermarking approach combining video and audio embedding with a temporal and cross-modal fusion mechanism for improved tampering detection.

Findings

Superior localization precision on tampering datasets

Enhanced robustness of watermark decoding

Effective coupling of audio and video copyright information

Abstract

AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia forensics. To solve this urgent issue, V2A-Mark is proposed to address the limitations of current video tampering forensics, such as poor generalizability, singular function, and single modality focus. Combining the fragility of video-into-video steganography with deep robust watermarking, our method can embed invisible visual-audio localization watermarks and copyright watermarks into the original video frames and audio, enabling precise manipulation localization and copyright protection. We also design a temporal alignment and fusion module and degradation prompt learning to enhance the localization accuracy and decoding robustness. Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames. The effectiveness of V2A-Mark has been verified on a visual-audio tampering dataset, emphasizing its superiority in localization precision and copyright accuracy, crucial for the sustainable development of video editing in the AIGC video era.