A Survey of Deep Fake Detection for Trial Courts

Authors: Naciye Celebi, Qingzhong Liu, Muhammed Karatoprak

Published: 2022-05-31 13:50:25+00:00

Comment: 12 Pages, 1 Table

AI Summary

This paper presents a comprehensive survey of methods and available datasets for DeepFake detection. It discusses the rapid advancement of DeepFake technologies, which can create realistic fake images and videos indistinguishable to humans, and the critical need for robust detection to prevent the spread of misinformation.

Abstract

Recently, image manipulation has achieved rapid growth due to the advancement of sophisticated image editing tools. A recent surge of generated fake imagery and videos using neural networks is DeepFake. DeepFake algorithms can create fake images and videos that humans cannot distinguish from authentic ones. (GANs) have been extensively used for creating realistic images without accessing the original images. Therefore, it is become essential to detect fake videos to avoid spreading false information. This paper presents a survey of methods used to detect DeepFakes and datasets available for detecting DeepFakes in the literature to date. We present extensive discussions and research trends related to DeepFake technologies.

Key findings

The paper highlights that DeepFakes are rapidly advancing, making it increasingly difficult for humans to distinguish them from authentic content. It underscores the critical need for robust deepfake detection methods and tools, especially for legal contexts where the authenticity of digital evidence is paramount. The survey concludes that AI-based detection is essential to counter advanced deepfake generation, as current capabilities may soon be outmatched by new generation techniques.

Approach

The paper provides a structured survey of existing deepfake detection techniques, available datasets, and the current research trends. It also discusses the legal implications of deepfakes for trial courts, emphasizing the challenges in authenticating digital evidence.

Datasets

Celeb-DF, FaceForensics++, DeepFake Detection (Google/Jigsaw), DeepFake Detection Preview (Facebook), HOHA Dataset, UADFV, DF-TIMIT, VTD Dataset

Model(s)

Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Neural Ordinary Differential Equations (Neural-ODE), Siamese Networks, SVM classifier, VGG16, ResNet50, OpenFace2 toolkit, Photo Response Non-Uniformity (PRNU) analysis

Author countries

USA

← Previous