Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness
This work addresses video forgery detection for security applications, offering an incremental improvement in imperceptibility and robustness over previous methods.
The paper tackles the problem of detecting tampered areas in videos by proposing a video watermarking network that embeds imperceptible watermarks and decodes them to predict tampering masks, achieving robust and accurate localization even under attacks like compression and blurring.
Videos are prone to tampering attacks that alter the meaning and deceive the audience. Previous video forgery detection schemes find tiny clues to locate the tampered areas. However, attackers can successfully evade supervision by destroying such clues using video compression or blurring. This paper proposes a video watermarking network for tampering localization. We jointly train a 3D-UNet-based watermark embedding network and a decoder that predicts the tampering mask. The perturbation made by watermark embedding is close to imperceptible. Considering that there is no off-the-shelf differentiable video codec simulator, we propose to mimic video compression by ensembling simulation results of other typical attacks, e.g., JPEG compression and blurring, as an approximation. Experimental results demonstrate that our method generates watermarked videos with good imperceptibility and robustly and accurately locates tampered areas within the attacked version.