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.
翻译:视频很容易被篡改,改变其含义并欺骗观众。 先前的视频伪造检测计划发现一些微小的线索可以定位被篡改的地区。 但是, 攻击者可以通过使用视频压缩或模糊来销毁这些线索, 从而成功逃避监督。 本文建议为篡改本地化设置一个视频水标记网络。 我们联合培训了一个基于 3D- UNet 的水标记嵌入网络和一个显示篡改面罩的解码器。 水标记嵌入造成的扰动接近无法察觉。 考虑到没有现成的不同视频编码模拟器, 我们提议通过模拟其他典型攻击的模拟结果来模拟视频压缩, 例如, JPEG 压缩和模糊, 作为一种近似。 实验结果显示, 我们的方法生成了水标记视频, 并且非常不易感知, 并且准确定位了被攻击版本中被篡改的区域 。