東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Digital Forensics and Analysis of De...

Jafar, Mousa Tayseer,

FindBook

Google Book

Amazon

博客來

Digital Forensics and Analysis of Deepfake Videos /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Digital Forensics and Analysis of Deepfake Videos // Mousa Tayseer Jafar.
作者:	Jafar, Mousa Tayseer,
面頁冊數:	1 electronic resource (171 pages)
附註:	Source: Masters Abstracts International, Volume: 83-04.
Contained By:	Masters Abstracts International83-04.
標題:	Law enforcement. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28148377
ISBN:	9798460473502

Digital Forensics and Analysis of Deepfake Videos /
Jafar, Mousa Tayseer,

Digital Forensics and Analysis of Deepfake Videos /Mousa Tayseer Jafar. - 1 electronic resource (171 pages)

Source: Masters Abstracts International, Volume: 83-04.

The rapid development of deep learning algorithms and artificial intelligence has led to the emergence of an algorithm that can generate a copy of a real human face, which can be completely controlled to say or to do anything. This is known as Deepfake.This has led to a major revolution in the field of information security and cybersecurity, with its futile effects and consequences on societies as well as a huge gap and vulnerability in the reality of the videos that are being published on the internet, especially those of presidents and world leaders. In this study, we will build a deep learning algorithm, convolutional neural network, consisting of 6 layers to analyze and detect fake videos that were produced from Deepfake based on an analysis of the characteristics of the teeth as a biological signal in fake videos and compare them with features from real videos. This model will specifically use voice as a frame filter to determine the mouth area and extract frames from real videos; consequently, the number of extracted frames will be decreased. The novel approach will be used to improve the flexibility and speed of detecting fake videos, as it depends on determining teeth in the mouth region as an essential part. In addition, this will lead to a reduction in the number of images that will be used to detect Deepfake. The latest Deepfake forensics dataset, Celeb-DF, was developed to evaluate the Deepfake detection algorithms that will be used in our model.

English

ISBN: 9798460473502Subjects--Topical Terms:

607408
Law enforcement.
Subjects--Index Terms:

Classification

Digital Forensics and Analysis of Deepfake Videos /
LDR:02914nmm a22004333i 4500 001 2437595
005 20251124054943.5
006 m o d
007 cr|nu||||||||
008 261011s2020 miu||||||m |||||||eng d
020 $a 9798460473502
035 $a (MiAaPQD)AAI28148377
035 $a AAI28148377
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Jafar, Mousa Tayseer, $e author. $3 3828641
245 1 0 $a Digital Forensics and Analysis of Deepfake Videos / $c Mousa Tayseer Jafar.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 1 electronic resource (171 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-04.
500 $a Advisors: Al-Rashdan, Ammar Committee members: Al-Fayoumi, Mustafa; Al-Zoube, Mohammad; Abu-Zitar, Raed Abdallah.
502 $b M.Sc.C. $c Princess Sumaya University for Technology (Jordan) $d 2020.
520 $a The rapid development of deep learning algorithms and artificial intelligence has led to the emergence of an algorithm that can generate a copy of a real human face, which can be completely controlled to say or to do anything. This is known as Deepfake.This has led to a major revolution in the field of information security and cybersecurity, with its futile effects and consequences on societies as well as a huge gap and vulnerability in the reality of the videos that are being published on the internet, especially those of presidents and world leaders. In this study, we will build a deep learning algorithm, convolutional neural network, consisting of 6 layers to analyze and detect fake videos that were produced from Deepfake based on an analysis of the characteristics of the teeth as a biological signal in fake videos and compare them with features from real videos. This model will specifically use voice as a frame filter to determine the mouth area and extract frames from real videos; consequently, the number of extracted frames will be decreased. The novel approach will be used to improve the flexibility and speed of detecting fake videos, as it depends on determining teeth in the mouth region as an essential part. In addition, this will lead to a reduction in the number of images that will be used to detect Deepfake. The latest Deepfake forensics dataset, Celeb-DF, was developed to evaluate the Deepfake detection algorithms that will be used in our model.
546 $a English
590 $a School code: 2116
650 4 $a Law enforcement. $3 607408
650 4 $a Artificial intelligence. $3 516317
650 4 $a Information science. $3 554358
653 $a Classification
653 $a Deep learning
653 $a Manipulation
653 $a Segmentation
653 $a Detection
690 $a 0800
690 $a 0723
690 $a 0206
710 2 $a Princess Sumaya University for Technology (Jordan). $b Department of Computer Science. $e degree granting institution. $3 3820652
720 1 $a Al-Rashdan, Ammar $e degree supervisor.
773 0 $t Masters Abstracts International $g 83-04.
790 $a 2116
791 $a M.Sc.C.
792 $a 2020
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28148377