New and existing methods for generating, and especially detecting, deepfakes are investigated and compared on the simple problem of authenticating coin flip data. Importantly, an alternative approach to deepfake generation and detection, which uses a Markov Observation Model (MOM) is introduced and compared on detection ability to the traditional Generative Adversarial Network (GAN) approach as well as Support Vector Machine (SVM), Branching Particle Filtering (BPF) and human alternatives. MOM was also compared on generative and discrimination ability to GAN, filtering and humans (as SVM does not have generative ability). Humans are shown to perform the worst, followed in order by GAN, SVM, BPF and MOM, which was the best at the detection of deepfakes. Unsurprisingly, the order was maintained on the generation problem with removal of SVM as it does not have generation ability.
翻译：本文研究并比较了在验证硬币抛掷数据这一简单问题上，用于生成（尤其是检测）深度伪造的新方法与现有方法。重要的是，我们引入了一种使用马尔可夫观测模型（MOM）的深度伪造生成与检测替代方法，并在检测能力上将其与传统的生成对抗网络（GAN）方法、支持向量机（SVM）、分支粒子滤波（BPF）以及人工方法进行了比较。MOM 还在生成与判别能力上与 GAN、滤波方法及人类（因 SVM 不具备生成能力）进行了比较。结果显示，人类表现最差，其次是 GAN、SVM、BPF 和 MOM，其中 MOM 在检测深度伪造方面表现最佳。不出所料，在生成问题上（因 SVM 不具备生成能力而将其排除），这一性能排序得以保持。
相关内容
微信扫码咨询专知VIP会员