A Survey of Deep Fake Detection for Trial Courts

View on arXiv ← Back to list

Authors: Naciye Celebi, Qingzhong Liu, Muhammed Karatoprak

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

AI Summary

This research paper provides a survey of deepfake detection methods and datasets. It discusses research trends in deepfake technologies and their implications for legal proceedings, particularly in trial courts.

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 survey highlights the rapid advancement of deepfake generation techniques and the growing need for robust detection methods. It emphasizes the challenges posed by deepfakes to legal proceedings and the importance of developing AI-based tools to authenticate digital evidence in court. The paper also notes that the number of available datasets for deepfake detection remains limited.

Approach

The paper surveys existing deepfake detection methods and datasets, analyzing various approaches such as those based on convolutional neural networks (CNNs), recurrent neural networks (RNNs), and analysis of visual movement fields. It also examines the legal implications of deepfakes in trial courts.

Datasets

Celeb-DF, FaceForensics++, DeepFake Detection, DeepFake Detection Preview, HOHA Dataset, UADFV, DF-TIMIT, VTD Dataset, Vid-TIMIT

Model(s)

Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Neural Ordinary Differential Equations (Neural-ODE), Support Vector Machines (SVM), Siamese networks

Author countries

USA

← Previous