The mushroomed Deepfake synthetic materials circulated on the internet have raised serious social impact to politicians, celebrities, and every human being on earth. In this survey, we provide a thorough review of the existing Deepfake detection studies from the reliability perspective. Reliability-oriented research challenges of the current Deepfake detection research domain are defined in three aspects, namely, transferability, interpretability, and robustness. While solutions have been frequently addressed regarding the three challenges, the general reliability of a detection model has been barely considered, leading to the lack of reliable evidence in real-life usages and even for prosecutions on Deepfake-related cases in court. We, therefore, introduce a model reliability study metric using statistical random sampling knowledge and the publicly available benchmark datasets to review the reliability of the existing detection models on arbitrary Deepfake candidate suspects. Case studies are further executed to justify the real-life Deepfake cases including different groups of victims with the help of the reliably qualified detection models as reviewed in this survey. Reviews and experiments upon the existing approaches provide informative discussions and future research directions of Deepfake detection.

翻译：摘要：互联网上大量涌现的Deepfake合成内容已对政治家、名人及全球公众产生严重的社会影响。本综述从可靠性视角对现有Deepfake检测研究进行了全面梳理。当前Deepfake检测研究领域中面向可靠性的研究挑战被定义为三个维度：可迁移性、可解释性和鲁棒性。尽管针对这三类挑战已有诸多解决方案，但检测模型的整体可靠性却鲜少被考量，导致实际应用场景乃至法庭中涉及Deepfake案件的司法审判缺乏可靠证据。为此，我们引入基于统计随机抽样知识与公开基准数据集的模型可靠性评估指标，对现有检测模型在任意疑似Deepfake候选对象上的可靠性进行系统评估。进一步通过案例研究，借助本综述评定的高可靠性检测模型，对包含不同受害者群体的真实Deepfake案例进行了验证。针对现有方法的综述与实验为Deepfake检测提供了具有启发性的讨论与未来研究方向。