Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets.Our code is available at \url{https://github.com/QingyuLiu/Exposing-the-Deception}, hoping to inspire researchers.

翻译：深度伪造技术催生了一系列新颖且引人注目的应用。然而，高保真虚假视频的广泛传播却导致了普遍的混淆与欺骗，动摇了我们“眼见为实”的信念。目前一个被忽视的问题是，现有的深度伪造检测方法容易陷入过拟合陷阱，仅关注一个或少数局部区域的伪造线索。此外，现有工作严重依赖神经网络提取伪造特征，缺乏理论约束来确保提取足够的伪造线索并消除冗余特征。这些缺陷导致在真实场景中检测精度欠佳且泛化能力有限。本文通过三种设计应对这些挑战：(1) 我们提出一种新型框架，通过提取多个非重叠的局部表征并将其融合为全局语义丰富的特征，捕获更广泛的伪造线索。(2) 基于信息瓶颈理论，我们推导出局部信息损失，在保证局部表征正交性的同时保留全面的任务相关信息。(3) 进一步，通过互信息的理论分析，我们得到全局信息损失以融合局部表征并移除任务无关信息。实验表明，我们的方法在五个基准数据集上达到了最先进性能。代码已开源至\url{https://github.com/QingyuLiu/Exposing-the-Deception}，期待激发更多研究。