Deep Insights of Deepfake Technology : A Review

View on arXiv ← Back to list

Authors: Bahar Uddin Mahmud, Afsana Sharmin

Published: 2021-05-01 08:25:43+00:00

AI Summary

This paper provides a review of Deepfake technology, examining its creation and detection techniques. It explores both the malicious and beneficial applications of Deepfakes, highlighting the need for countermeasures and regulations to mitigate its harmful potential.

Abstract

Under the aegis of computer vision and deep learning technology, a new emerging techniques has introduced that anyone can make highly realistic but fake videos, images even can manipulates the voices. This technology is widely known as Deepfake Technology. Although it seems interesting techniques to make fake videos or image of something or some individuals but it could spread as misinformation via internet. Deepfake contents could be dangerous for individuals as well as for our communities, organizations, countries religions etc. As Deepfake content creation involve a high level expertise with combination of several algorithms of deep learning, it seems almost real and genuine and difficult to differentiate. In this paper, a wide range of articles have been examined to understand Deepfake technology more extensively. We have examined several articles to find some insights such as what is Deepfake, who are responsible for this, is there any benefits of Deepfake and what are the challenges of this technology. We have also examined several creation and detection techniques. Our study revealed that although Deepfake is a threat to our societies, proper measures and strict regulations could prevent this.

Key findings

The review reveals a rapid advancement in both Deepfake generation and detection techniques. The ease of Deepfake creation poses significant risks, particularly in spreading misinformation and causing harm. However, the technology also presents positive applications in fields like film and education.

Approach

The paper reviews existing literature on Deepfake generation and detection methods, analyzing various techniques, tools, and datasets used in both processes. It examines both the positive and negative societal impacts of Deepfake technology.

Datasets

VidTIMIT database (for Deepfake video generation and evaluation)

Model(s)

Various deep learning models are mentioned, including autoencoders, GANs, CNNs, RNNs, LSTMs, and specific architectures like VGG, Facenet, DenseNet, ResNet, and Capsule networks. Specific Deepfake creation tools like FakeApp, FaceSwap, FaceSwap-GAN, Faceswap-pytorch, DeepFaceLab, and DFaker are also discussed.

Author countries

Bangladesh

← Previous