文章基本信息

标题：DEEPFAKES: THREATS AND COUNTERMEASURES: SYSTEMATIC REVIEW
本地全文：下载
作者：MARWAN ALBAHAR ; JAMEEL ALMALKI
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：22
页码：3242-3250
出版社：Journal of Theoretical and Applied
摘要：Deepfake, a machine learning-based software tool, has made it easy to alter or manipulate images and videos. Images are frequently used as evidence in investigations and in court. However, technological developments, and deepfake in particular, have potentially made these pieces of evidence unreliable. Altered images and videos are not only surprisingly convincing but are also difficult to identify as fake or real. Deepfakes have been used to blackmail, fake terrorism events, disseminate fake news, defame individuals, and to create political distress. To gain in-depth insight into the deepfake technology, the present research examines its origin and history while assessing how deepfake videos and photos are created. Moreover, the research also focuses on the impact deepfake has made on society in terms of how it has been applied. Different methods have been developed for detecting deepfakes including face detection, multimedia forensics, watermarking, and convolutional neural networks (CNNs). Each method uses machine learning, a technique from the field of artificial intelligence, to detect any kind of manipulation in photos and videos.
关键词：Authentication; Deepfake; Video Evidence; Artificial Intelligence