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 Generation for Use in Dicti...

Barros, Vasco Mucha,

Linked to FindBook

Google Book

Amazon

博客來

Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems // Vasco Mucha Barros.
Author:	Barros, Vasco Mucha,
Description:	1 electronic resource (69 pages)
Notes:	Source: Masters Abstracts International, Volume: 86-02.
Contained By:	Masters Abstracts International86-02.
Subject:	Communication channels. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31161353
ISBN:	9798383778876

Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems /
Barros, Vasco Mucha,

Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems /Vasco Mucha Barros. - 1 electronic resource (69 pages)

Source: Masters Abstracts International, Volume: 86-02.

Biometric authentication, although not new, is seeing an increase in popularity and usage in current times, particularly facial recognition. At the same time, image manipulation technology is also booming, with software becoming accessible to virtually anyone who has an above-average machine. Deep learning, though deepfakes, is already a cause of concern due to its usage in manipulated content such as fake news, in an era of digital information. As facial recognition becomes more prominent in people's daily lives, the chances for deepfakes to be used maliciously in that another field should not be ignored.In order to analyze the extents of the vulnerabilities of these systems, we propose training a Generative Adversarial Network that generates a particular type of deepfake, and then using those fakes, testing whether or not various systems recognize them as real faces and furthermore whether they can or not breach the systems' security. The reasoning for the specific particularity of the fakes is discussed further ahead.In addition to that, we discuss the concerning results produced by some of the previous works on this topic, as well as how those could still be taken even further if different attacking angles are combined into a single attack. To contrast, we also talk about anti-deepfake tools and how they can prove to be crucial to combat these new type of threats to facial authentication systems.

English

ISBN: 9798383778876Subjects--Topical Terms:

3560268
Communication channels.

Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems /
LDR:02838nmm a22004093i 4500 001 2437674
005 20251124054955.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798383778876
035 $a (MiAaPQD)AAI31161353
035 $a (MiAaPQD)Portugal10216156472
035 $a AAI31161353
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Barros, Vasco Mucha, $e author. $3 3828740
245 1 0 $a Deepfake Generation for Use in Dictionary Attacks on Facial Recognition Systems / $c Vasco Mucha Barros.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (69 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: 86-02.
500 $a Advisors: Antunes, Mario Joao Goncalves; Correia, Manuel Eduardo Carvalho Duarte.
502 $b M.C.E. $c Universidade do Porto (Portugal) $d 2023.
520 $a Biometric authentication, although not new, is seeing an increase in popularity and usage in current times, particularly facial recognition. At the same time, image manipulation technology is also booming, with software becoming accessible to virtually anyone who has an above-average machine. Deep learning, though deepfakes, is already a cause of concern due to its usage in manipulated content such as fake news, in an era of digital information. As facial recognition becomes more prominent in people's daily lives, the chances for deepfakes to be used maliciously in that another field should not be ignored.In order to analyze the extents of the vulnerabilities of these systems, we propose training a Generative Adversarial Network that generates a particular type of deepfake, and then using those fakes, testing whether or not various systems recognize them as real faces and furthermore whether they can or not breach the systems' security. The reasoning for the specific particularity of the fakes is discussed further ahead.In addition to that, we discuss the concerning results produced by some of the previous works on this topic, as well as how those could still be taken even further if different attacking angles are combined into a single attack. To contrast, we also talk about anti-deepfake tools and how they can prove to be crucial to combat these new type of threats to facial authentication systems.
546 $a English
590 $a School code: 5896
650 4 $a Communication channels. $3 3560268
650 4 $a Deep learning. $3 3554982
650 4 $a Deepfake. $3 3828727
650 4 $a Biometrics. $3 898232
650 4 $a Neural networks. $3 677449
650 4 $a Facial recognition technology. $3 3687251
650 4 $a Communication. $3 524709
650 4 $a Computer science. $3 523869
650 4 $a Information technology. $3 532993
690 $a 0800
690 $a 0459
690 $a 0984
690 $a 0489
710 2 $a Universidade do Porto (Portugal). $e degree granting institution. $3 3815379
720 1 $a Antunes, Mario Joao Goncalves $e degree supervisor.
720 1 $a Correia, Manuel Eduardo Carvalho Duarte $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-02.
790 $a 5896
791 $a M.C.E.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31161353