V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection
This addresses the challenge of multimedia forensics in AI-generated video content, which is crucial for video editing in the AIGC era, though it appears incremental as it builds on existing watermarking techniques.
The paper tackles the problem of detecting manipulated AI-generated videos by proposing V2A-Mark, a deep visual-audio watermarking method that embeds invisible watermarks for manipulation localization and copyright protection, achieving superior localization precision and copyright accuracy on a visual-audio tampering dataset.
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.