摘要
Deepfakes代表了一类借助先进深度学习技术精心制作的合成媒体，显示出无与伦比的真实性。人工智能(AI)的迅速发展促进了互联网上深度伪造的流行，从而放大了错误信息在公众中的传播。因此，检测深度假货已成为一个紧迫的问题。在此背景下，我们提出了一个基于三个不同层次的深度假视频检测的综合框架。第一层被称为RGB特征提取层，用于识别类似视频帧的空域内的潜在伪造标志。第二层，即GAN特征提取层，主要研究高频区域伪造指纹的提取。该层是专门设计用来检测生成性对抗网络(GAN)过程在假视频中留下的指纹和真实视频中成像过程的痕迹。第三层也是最后一层，被称为面部区域帧内不一致特征提取层，致力于揭示与操作过程相关的异常。这是通过从帧的操纵部分的内部和外部区域提取特征来实现的。广泛的实验评估强调了与现有最先进的方法相比，所提出的方法的优越性能。
Abstract
Deepfakes represent a class of synthetic media crafted with the aid of advanced deep learning techniques that exhibit an unparalleled degree of authenticity. The rapid advancement in Artificial Intelligence (AI) has contributed to an increase in the prevalence of deepfakes on the internet, consequently amplifying the spread of misinformation among the public. Consequently, the detection of deepfakes has become a pressing concern. In this context, we put forth a comprehensive framework for deepfake video detection, which is built upon three distinct layers. The first layer, termed as the RGB features extraction layer, is designed to identify potential signs of forgery within the spatial domain of analogous video frames. The second layer, known as the GAN features extraction layer, focuses on the extraction of forgery fingerprints in the high-frequency region. This layer is specifically engineered to detect the fingerprints left by the Generative Adversarial Network (GAN) process in fake videos and the traces of the imaging process in genuine videos. The third and final layer, referred to as the facial region intra-frame inconsistency feature extraction layer, is dedicated to uncovering the anomalies associated with the manipulation process. This is achieved by extracting features from both the inner and outer regions of the manipulated portion of a frame. The extensive experimental evaluations have underscored the superior performance of proposed approach in comparison to existing state-of-the-art methods.
NETL
NSTL