Markov Processes for Enhanced Deepfake Generation and Detection

TL;DR

This paper introduces a Markov Observation Model (MOM) for deepfake detection, demonstrating its superior performance over GANs, SVMs, BPF, and humans in authenticating coin flip data, and compares its generative and discriminative capabilities.

Contribution

The paper proposes a novel MOM approach for deepfake detection and compares it with traditional methods and humans, highlighting its improved detection accuracy.

Findings

MOM outperforms GAN, SVM, BPF, and humans in deepfake detection.

Humans perform the worst, MOM performs the best in detection.

Order of performance is consistent in generation and detection tasks.

Abstract

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.