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

Integrity and Privacy in Adversarial Machine Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Integrity and Privacy in Adversarial Machine Learning./
作者:	Jagielski, Matthew.
面頁冊數:	1 online resource (175 pages)
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28652549click for full text (PQDT)
ISBN:	9798535516004

Integrity and Privacy in Adversarial Machine Learning.
Jagielski, Matthew.

Integrity and Privacy in Adversarial Machine Learning. - 1 online resource (175 pages)

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Northeastern University, 2021.

Includes bibliographical references

Machine learning is being used for an increasing number of applications with societal impact. In such settings, models must be trusted to be fair, useful, and robust. In many applications, a large amount of training data is collected from a variety of sources, including from private or untrusted individuals. Manually sanitizing datasets is difficult as datasets increase in size, which allows a motivate adversary to adversarially corrupt training data, crafted to impact the model at test time, referred to as a poisoning attack. These poisoning attacks can cause specific users' data to be misclassified, which can be harmful if models are applied to sensitive tasks such as security applications. At the same time, models trained on datasets collected from real people must protect their privacy, preventing unscrupulous onlookers from learning more than they should; in sensitive domains such as personalized medicine, privacy is of utmost importance.In this thesis, we describe integrity and privacy vulnerabilities in these critical settings. We explore the variety of adversarial goals that can be accomplished with poisoning, and how to construct defenses against these attacks (if this is possible at all). Our work will high-light the difficulty of developing generic poisoning defenses; dependence on the adversarial objective appears to be necessary for large enough attacks. Next, we discuss the connection between differential privacy and poisoning attacks, showing that poisoning can be useful for interpreting privacy guarantees, and differential privacy may not serve as a defense from poisoning attacks. Finally, we discuss privacy leakage in the realistic training setting where models are updated repeatedly over time. Our privacy attacks highlight and tackle the current challenges in deploying private algorithms in real world settings. Overall, this thesis will demonstrate the diversity of types of both poisoning attacks and privacy attacks and the challenges in defending against these attacks and securing machine learning in critical settings.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798535516004Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Adversarial machine learningIndex Terms--Genre/Form:

542853
Electronic books.

Integrity and Privacy in Adversarial Machine Learning.
LDR:03467nmm a2200397K 4500 001 2357227
005 20230622065021.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798535516004
035 $a (MiAaPQ)AAI28652549
035 $a AAI28652549
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jagielski, Matthew. $3 3697757
245 1 0 $a Integrity and Privacy in Adversarial Machine Learning.
264 0 $c 2021
300 $a 1 online resource (175 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: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Nita-Rotaru, Cristina; Oprea, Alina.
502 $a Thesis (Ph.D.)--Northeastern University, 2021.
504 $a Includes bibliographical references
520 $a Machine learning is being used for an increasing number of applications with societal impact. In such settings, models must be trusted to be fair, useful, and robust. In many applications, a large amount of training data is collected from a variety of sources, including from private or untrusted individuals. Manually sanitizing datasets is difficult as datasets increase in size, which allows a motivate adversary to adversarially corrupt training data, crafted to impact the model at test time, referred to as a poisoning attack. These poisoning attacks can cause specific users' data to be misclassified, which can be harmful if models are applied to sensitive tasks such as security applications. At the same time, models trained on datasets collected from real people must protect their privacy, preventing unscrupulous onlookers from learning more than they should; in sensitive domains such as personalized medicine, privacy is of utmost importance.In this thesis, we describe integrity and privacy vulnerabilities in these critical settings. We explore the variety of adversarial goals that can be accomplished with poisoning, and how to construct defenses against these attacks (if this is possible at all). Our work will high-light the difficulty of developing generic poisoning defenses; dependence on the adversarial objective appears to be necessary for large enough attacks. Next, we discuss the connection between differential privacy and poisoning attacks, showing that poisoning can be useful for interpreting privacy guarantees, and differential privacy may not serve as a defense from poisoning attacks. Finally, we discuss privacy leakage in the realistic training setting where models are updated repeatedly over time. Our privacy attacks highlight and tackle the current challenges in deploying private algorithms in real world settings. Overall, this thesis will demonstrate the diversity of types of both poisoning attacks and privacy attacks and the challenges in defending against these attacks and securing machine learning in critical settings.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Datasets. $3 3541416
650 4 $a Poisoning. $3 770903
650 4 $a Privacy. $3 528582
650 4 $a Neural networks. $3 677449
653 $a Adversarial machine learning
653 $a Data poisoning
653 $a Differential privacy
653 $a Fairness
653 $a Machine learning privacy
653 $a Robustness
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Northeastern University. $b Computer Science. $3 1678818
773 0 $t Dissertations Abstracts International $g 83-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28652549 $z click for full text (PQDT)