國立虎尾科技大學 |

Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox./
作者:	Dave, Krishna.
面頁冊數:	1 online resource (82 pages)
附註:	Source: Masters Abstracts International, Volume: 85-09.
Contained By:	Masters Abstracts International85-09.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798381959468

Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox.
Dave, Krishna.

Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox. - 1 online resource (82 pages)

Source: Masters Abstracts International, Volume: 85-09.

Thesis (M.S.)--University of California, Los Angeles, 2024.

Includes bibliographical references

In today's world with ever increasing need for data collection, there is a rise in demand for privacy-preserving synthetic data generation and privacy auditing techniques to safeguard sensitive user information and data from privacy attacks. This paper explores the adversarial privacy auditing of synthetically generated data produced by Large Language Models (LLMs) using the TAPAS "Toolbox for Adversarial Privacy Auditing of Synthetic Data" framework. This paper uses a healthcare dataset with sensitive user information of Breast Cancer to evaluate the privacy of the data using adversarial techniques. The paper compares and contrasts the data quality, data distributions and privacy-preserving metrics of the real dataset with synthetically generated datasets from several sources including LLMs such as the GReaT framework and OpenAI's GPT4, Generative Adversarial Networks (GANs), and an AI-generated dataset produced using a proprietary technique from an industry startup, mostly.ai.

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

Mode of access: World Wide Web

ISBN: 9798381959468Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Adversarial techniquesIndex Terms--Genre/Form:

554714
Electronic books.

Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox.
LDR:02449ntm a22004097 4500 001 1146450
005 20240812064619.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798381959468
035 $a (MiAaPQ)AAI30993756
035 $a AAI30993756
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Dave, Krishna. $3 1471839
245 1 0 $a Adversarial Privacy Auditing of Synthetically Generated Data Produced by Large Language Models Using the TAPAS Toolbox.
264 0 $c 2024
300 $a 1 online resource (82 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: 85-09.
500 $a Advisor: Cheng, Guang.
502 $a Thesis (M.S.)--University of California, Los Angeles, 2024.
504 $a Includes bibliographical references
520 $a In today's world with ever increasing need for data collection, there is a rise in demand for privacy-preserving synthetic data generation and privacy auditing techniques to safeguard sensitive user information and data from privacy attacks. This paper explores the adversarial privacy auditing of synthetically generated data produced by Large Language Models (LLMs) using the TAPAS "Toolbox for Adversarial Privacy Auditing of Synthetic Data" framework. This paper uses a healthcare dataset with sensitive user information of Breast Cancer to evaluate the privacy of the data using adversarial techniques. The paper compares and contrasts the data quality, data distributions and privacy-preserving metrics of the real dataset with synthetically generated datasets from several sources including LLMs such as the GReaT framework and OpenAI's GPT4, Generative Adversarial Networks (GANs), and an AI-generated dataset produced using a proprietary technique from an industry startup, mostly.ai.
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
650 4 $a Statistics. $3 556824
653 $a Adversarial techniques
653 $a Large Language Models
653 $a Machine learning
653 $a Privacy auditing
653 $a Synthetically generated data
653 $a TAPAS toolbox
655 7 $a Electronic books. $2 local $3 554714
690 $a 0463
690 $a 0984
690 $a 0800
710 2 $a University of California, Los Angeles. $b Applied Statistics And Data Science 00J3. $3 1471761
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-09.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30993756 $z click for full text (PQDT)