國立虎尾科技大學 |

Deepfake Video Detection Using Human Facial Features.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Deepfake Video Detection Using Human Facial Features./
作者:	Ademiluyi, Desmond Toye.
面頁冊數:	1 online resource (130 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-09, Section: B.
Contained By:	Dissertations Abstracts International84-09B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798374418095

Deepfake Video Detection Using Human Facial Features.
Ademiluyi, Desmond Toye.

Deepfake Video Detection Using Human Facial Features. - 1 online resource (130 pages)

Source: Dissertations Abstracts International, Volume: 84-09, Section: B.

Thesis (D.Sc.)--Aspen University, 2023.

Includes bibliographical references

Deepfake technology can be used to replace people's faces in videos or pictures to show them saying or doing things they never said or did. Deepfake media are often used to extort, defame, and manipulate public opinion. However, despite deepfake technology's risks, current deepfake detection methods lack generalization and are inconsistent when applied to unknown videos, i.e., videos on which they have not been trained. The purpose of this study is to develop a generalizable deepfake detection model by training convoluted neural networks (CNNs) to classify human facial features in videos. The study formulated three research questions: "How does training the model with only human faces affect its accuracy?"; "How effectively does the developed model provide reliable generalization?"; and "How accurate is the developed model compared to existing deepfake detection methods?" A CNN model was trained to distinguish between real and fake videos using the facial features of human subjects in videos. The model was trained, validated, and tested using the FaceForensiq++ dataset, which contains more than 500,000 frames and subsets of the DFDC dataset, totaling more than 22,000 videos. The study demonstrated a 10% improvement in accuracy over current deepfake detection methods. In addition, the model was generalizable, as the accuracy of the unknown dataset was only marginally (about 1%) lower than that of the known dataset. The findings of this study indicate that detection systems can be more generalizable, lighter, and faster by focusing on just a small region (the human face) of an entire video.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798374418095Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Artificial intelligenceIndex Terms--Genre/Form:

554714
Electronic books.

Deepfake Video Detection Using Human Facial Features.
LDR:02911ntm a22003737 4500 001 1145562
005 20240624103338.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798374418095
035 $a (MiAaPQ)AAI30248539
035 $a AAI30248539
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ademiluyi, Desmond Toye. $3 1470723
245 1 0 $a Deepfake Video Detection Using Human Facial Features.
264 0 $c 2023
300 $a 1 online resource (130 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: Dissertations Abstracts International, Volume: 84-09, Section: B.
500 $a Advisor: Nguyen, Dan S.
502 $a Thesis (D.Sc.)--Aspen University, 2023.
504 $a Includes bibliographical references
520 $a Deepfake technology can be used to replace people's faces in videos or pictures to show them saying or doing things they never said or did. Deepfake media are often used to extort, defame, and manipulate public opinion. However, despite deepfake technology's risks, current deepfake detection methods lack generalization and are inconsistent when applied to unknown videos, i.e., videos on which they have not been trained. The purpose of this study is to develop a generalizable deepfake detection model by training convoluted neural networks (CNNs) to classify human facial features in videos. The study formulated three research questions: "How does training the model with only human faces affect its accuracy?"; "How effectively does the developed model provide reliable generalization?"; and "How accurate is the developed model compared to existing deepfake detection methods?" A CNN model was trained to distinguish between real and fake videos using the facial features of human subjects in videos. The model was trained, validated, and tested using the FaceForensiq++ dataset, which contains more than 500,000 frames and subsets of the DFDC dataset, totaling more than 22,000 videos. The study demonstrated a 10% improvement in accuracy over current deepfake detection methods. In addition, the model was generalizable, as the accuracy of the unknown dataset was only marginally (about 1%) lower than that of the known dataset. The findings of this study indicate that detection systems can be more generalizable, lighter, and faster by focusing on just a small region (the human face) of an entire video.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Artificial intelligence
653 $a Convoluted Neural Networks
653 $a Deep Learning
653 $a Deepfake
653 $a GANs
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Aspen University. $b School of Business & Technology. $3 1437776
773 0 $t Dissertations Abstracts International $g 84-09B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30248539 $z click for full text (PQDT)