國立虎尾科技大學 |

Assessing Vulnerability in Variational Autoencoder GANs : = Insights From White Box and Black Box Attack Scenarios.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Assessing Vulnerability in Variational Autoencoder GANs :/
其他題名:	Insights From White Box and Black Box Attack Scenarios.
作者:	Tangirala, Srivatsa.
面頁冊數:	1 online resource (43 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Information science. -
電子資源:	click for full text (PQDT)
ISBN:	9798383057704

Assessing Vulnerability in Variational Autoencoder GANs : = Insights From White Box and Black Box Attack Scenarios.
Tangirala, Srivatsa.

Assessing Vulnerability in Variational Autoencoder GANs :Insights From White Box and Black Box Attack Scenarios. - 1 online resource (43 pages)

Source: Masters Abstracts International, Volume: 85-12.

Thesis (M.S.)--Southern Illinois University at Carbondale, 2024.

Includes bibliographical references

In this study, we explore the vulnerability of Variational Autoencoder Generative Adversarial Networks (VAEGANs) to membership inference attacks, focusing on the potential privacy risks associated with Generative AI. By employing both black-box and white-box attack methodologies, we aim to quantify the extent to which sensitive information can be discerned or reconstructed by an adversary. Our investigation reveals significant vulnerabilities within the VAEGAN framework, highlighting the pressing need for enhanced privacy protections in generative models. Through a series of experiments across diverse datasets, we assess the impact of these attacks on the integrity of the models, shedding light on the balance between data generation capabilities and privacy preservation. Our findings underscore the importance of developing robust mechanisms to safeguard against such privacy breaches, contributing to the broader discussion on securing Generative AI against emerging threats.

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

Mode of access: World Wide Web

ISBN: 9798383057704Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Privacy preservationIndex Terms--Genre/Form:

554714
Electronic books.

Assessing Vulnerability in Variational Autoencoder GANs : = Insights From White Box and Black Box Attack Scenarios.
LDR:02342ntm a22003737 4500 001 1150175
005 20241022111607.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383057704
035 $a (MiAaPQ)AAI31146059
035 $a AAI31146059
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Tangirala, Srivatsa. $3 1476611
245 1 0 $a Assessing Vulnerability in Variational Autoencoder GANs : $b Insights From White Box and Black Box Attack Scenarios.
264 0 $c 2024
300 $a 1 online resource (43 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: 85-12.
500 $a Advisor: Imteaj, Ahmed.
502 $a Thesis (M.S.)--Southern Illinois University at Carbondale, 2024.
504 $a Includes bibliographical references
520 $a In this study, we explore the vulnerability of Variational Autoencoder Generative Adversarial Networks (VAEGANs) to membership inference attacks, focusing on the potential privacy risks associated with Generative AI. By employing both black-box and white-box attack methodologies, we aim to quantify the extent to which sensitive information can be discerned or reconstructed by an adversary. Our investigation reveals significant vulnerabilities within the VAEGAN framework, highlighting the pressing need for enhanced privacy protections in generative models. Through a series of experiments across diverse datasets, we assess the impact of these attacks on the integrity of the models, shedding light on the balance between data generation capabilities and privacy preservation. Our findings underscore the importance of developing robust mechanisms to safeguard against such privacy breaches, contributing to the broader discussion on securing Generative AI against emerging threats.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Computer science. $3 573171
653 $a Privacy preservation
653 $a Generative models
653 $a Data generation capabilities
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a Southern Illinois University at Carbondale. $b Computer Science. $3 1190734
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31146059 $z click for full text (PQDT)