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

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Exposing GAN-Generated Faces Using Deep Neural Network.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Exposing GAN-Generated Faces Using Deep Neural Network./
作者:	Guo, Hui.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	79 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
Contained By:	Dissertations Abstracts International83-12B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29210318
ISBN:	9798438795919

Exposing GAN-Generated Faces Using Deep Neural Network.
Guo, Hui.

Exposing GAN-Generated Faces Using Deep Neural Network. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 79 p.

Source: Dissertations Abstracts International, Volume: 83-12, Section: B.

Thesis (Ph.D.)--State University of New York at Albany, 2022.

This item must not be sold to any third party vendors.

Generative adversarial network (GAN) generated high-realistic human faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts. In this work, we explore a universal physiological cue of the eye, namely the pupil shape consistency, to identify GAN-generated faces reliably. We show that GAN-generated faces can be exposed via irregular pupil shapes. This phenomenon is caused by the lack of physiological constraints in the GAN models. We demonstrate that such artifacts exist widely in high-quality GAN-generated faces. We design an automatic method to segment the pupils from the eyes and analyze their shapes to distinguish GAN-generated faces from real ones. Furthermore, we propose a robust, attentive, end-to-end framework that spots GAN-generated faces by analyzing iris regions. The framework can automatically localize and compare artifacts between iris to identify GAN-generated faces. Once Mask-RCNN extracts the iris regions, a Residual Attention Network (RAN) is used to examine the components between the two iris. Besides, we use a joint loss function combining the traditional cross-entropy loss with a relaxation of the ROC-AUC loss via WMW statistics to improve the deep neural network learning from imbalanced data. Comprehensive evaluations demonstrate the superiority of the proposed methods.

ISBN: 9798438795919Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

GAN-generated faces

Exposing GAN-Generated Faces Using Deep Neural Network.
LDR:02560nmm a2200337 4500 001 2350421
005 20221020125800.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798438795919
035 $a (MiAaPQ)AAI29210318
035 $a AAI29210318
040 $a MiAaPQ $c MiAaPQ
100 1 $a Guo, Hui. $3 3626162
245 1 0 $a Exposing GAN-Generated Faces Using Deep Neural Network.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 79 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
500 $a Advisor: Chang, Ming-Ching.
502 $a Thesis (Ph.D.)--State University of New York at Albany, 2022.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a Generative adversarial network (GAN) generated high-realistic human faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts. In this work, we explore a universal physiological cue of the eye, namely the pupil shape consistency, to identify GAN-generated faces reliably. We show that GAN-generated faces can be exposed via irregular pupil shapes. This phenomenon is caused by the lack of physiological constraints in the GAN models. We demonstrate that such artifacts exist widely in high-quality GAN-generated faces. We design an automatic method to segment the pupils from the eyes and analyze their shapes to distinguish GAN-generated faces from real ones. Furthermore, we propose a robust, attentive, end-to-end framework that spots GAN-generated faces by analyzing iris regions. The framework can automatically localize and compare artifacts between iris to identify GAN-generated faces. Once Mask-RCNN extracts the iris regions, a Residual Attention Network (RAN) is used to examine the components between the two iris. Besides, we use a joint loss function combining the traditional cross-entropy loss with a relaxation of the ROC-AUC loss via WMW statistics to improve the deep neural network learning from imbalanced data. Comprehensive evaluations demonstrate the superiority of the proposed methods.
590 $a School code: 0668.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
653 $a GAN-generated faces
653 $a Generative adversarial network
690 $a 0984
690 $a 0800
710 2 $a State University of New York at Albany. $b Computer Science. $3 1681272
773 0 $t Dissertations Abstracts International $g 83-12B.
790 $a 0668
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29210318