東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Deepfake Detection through Motion Ma...

Mirzayev, Aydamir,

Linked to FindBook

Google Book

Amazon

博客來

Deepfake Detection through Motion Magnification Inspired Feature Manipulation = = Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deepfake Detection through Motion Magnification Inspired Feature Manipulation =/ Aydamir Mirzayev.
Reminder of title:	Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti /
Author:	Mirzayev, Aydamir,
Description:	1 electronic resource (62 pages)
Notes:	Source: Masters Abstracts International, Volume: 86-03.
Contained By:	Masters Abstracts International86-03.
Subject:	Photographs. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31302437
ISBN:	9798384198178

Deepfake Detection through Motion Magnification Inspired Feature Manipulation = = Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti /
Mirzayev, Aydamir,

Deepfake Detection through Motion Magnification Inspired Feature Manipulation =Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti /Aydamir Mirzayev. - 1 electronic resource (62 pages)

Source: Masters Abstracts International, Volume: 86-03.

Synthetically generated media content poses a significant threat to information security in the online domain. Manipulated videos and images of celebrities, politicians, and ordinary citizens, if aimed at misrepresentation, and defamation can cause significant damage to one's reputation. Early detection of such content is crucial to timely alleviation of further spread of questionable information. In the past years, a significant number of deepfake detection frameworks have proposed to utilize motion magnification as a preprocessing step aimed at revealing transitional inconsistencies relevant to the prediction outcome. However, such an approach is sub-optimal since often utilized motion manipulation approaches are optimized for a limited set of controlled motions and display significant visual artifacts when used outside of their domain. To this end, rather than apply motion magnification as a separate processing step, we propose to test trainable motion magnification-inspired feature manipulation units as an addition to a convolutional-LSTM classification network. In our approach, we aim to take the first step at understanding the use of magnification-like architectures in the task of video classification rather than aim at full integration. We test out results on the Celeb-DF dataset which is composed of more than five thousand synthetically generated videos generated using DeepFakes fake generation method. We treat manipulation unit as another network layer and test the performance of the network both with and without it. To ensure the consistency of our results we perform multiple experiments with the same configurations and report the average accuracy. In our experiments we observe an average 3% jump accuracy when the feature manipulation unit is incorporated into the network.

English

ISBN: 9798384198178Subjects--Topical Terms:

627415
Photographs.

Deepfake Detection through Motion Magnification Inspired Feature Manipulation = = Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti /
LDR:03229nmm a22004333i 4500 001 2437681
005 20251124054956.5
006 m o d
007 cr|nu||||||||
008 261011s2022 miu||||||m |||||||eng d
020 $a 9798384198178
035 $a (MiAaPQD)AAI31302437
035 $a (MiAaPQD)Bilkent_11693110538
035 $a AAI31302437
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Mirzayev, Aydamir, $e author. $3 3828748
245 1 0 $a Deepfake Detection through Motion Magnification Inspired Feature Manipulation = $b Hareket Buyutmesinden Esinlenen Oznitelik Manipulasyonu ile Derin Sahtelerin Tespiti / $c Aydamir Mirzayev.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 1 electronic resource (62 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: 86-03.
500 $a Advisors: Dibeklioglu, Hamdi.
502 $b M.S. $c Bilkent Universitesi (Turkey) $d 2022.
520 $a Synthetically generated media content poses a significant threat to information security in the online domain. Manipulated videos and images of celebrities, politicians, and ordinary citizens, if aimed at misrepresentation, and defamation can cause significant damage to one's reputation. Early detection of such content is crucial to timely alleviation of further spread of questionable information. In the past years, a significant number of deepfake detection frameworks have proposed to utilize motion magnification as a preprocessing step aimed at revealing transitional inconsistencies relevant to the prediction outcome. However, such an approach is sub-optimal since often utilized motion manipulation approaches are optimized for a limited set of controlled motions and display significant visual artifacts when used outside of their domain. To this end, rather than apply motion magnification as a separate processing step, we propose to test trainable motion magnification-inspired feature manipulation units as an addition to a convolutional-LSTM classification network. In our approach, we aim to take the first step at understanding the use of magnification-like architectures in the task of video classification rather than aim at full integration. We test out results on the Celeb-DF dataset which is composed of more than five thousand synthetically generated videos generated using DeepFakes fake generation method. We treat manipulation unit as another network layer and test the performance of the network both with and without it. To ensure the consistency of our results we perform multiple experiments with the same configurations and report the average accuracy. In our experiments we observe an average 3% jump accuracy when the feature manipulation unit is incorporated into the network.
546 $a English
590 $a School code: 1159
650 4 $a Photographs. $3 627415
650 4 $a Deep learning. $3 3554982
650 4 $a Deepfake. $3 3828727
650 4 $a Forensic sciences. $3 606870
650 4 $a Video recordings. $3 575241
650 4 $a Signal processing. $3 533904
650 4 $a Adjustment. $3 3680676
650 4 $a Neural networks. $3 677449
650 4 $a Art. $3 516292
650 4 $a False information. $3 3564362
650 4 $a Ordinary differential equations. $3 3563004
650 4 $a Image. $2 rasuqam $3 1548898
650 4 $a Linear algebra. $3 2923381
650 4 $a Semantics. $3 520060
650 4 $a Electrical engineering. $3 649834
650 4 $a Film studies. $3 2122736
650 4 $a Web studies. $3 2122754
650 4 $a Logic. $3 529544
650 4 $a Mathematics. $3 515831
690 $a 0774
690 $a 0800
690 $a 0544
690 $a 0900
690 $a 0646
690 $a 0395
690 $a 0405
710 2 $a Bilkent Universitesi (Turkey). $e degree granting institution. $3 3767555
720 1 $a Dibeklioglu, Hamdi $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-03.
790 $a 1159
791 $a M.S.
792 $a 2022
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31302437