國立虎尾科技大學 |

Machine Learning and Security in Adversarial Settings.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Machine Learning and Security in Adversarial Settings./
作者:	Aghakhani, Hojjat.
面頁冊數:	1 online resource (251 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798380158336

Machine Learning and Security in Adversarial Settings.
Aghakhani, Hojjat.

Machine Learning and Security in Adversarial Settings. - 1 online resource (251 pages)

Source: Dissertations Abstracts International, Volume: 85-02, Section: B.

Thesis (Ph.D.)--University of California, Santa Barbara, 2023.

Includes bibliographical references

Recent advancements in Machine Learning (ML) and growing computing power have led to the increased use of ML-based systems in security-critical applications such as face recognition, fingerprint identification, and malware detection, as well as in high-stakes applications like autonomous driving. However, as these systems become more prevalent, it is crucial to consider their risks and limitations carefully and to develop robust and secure systems that can withstand attacks.In this dissertation, I employ theoretical analysis and empirical evaluation to advance the understanding at the intersection of Machine Learning and Computer Security. Specifically, I present novel ML-based approaches to address security-related problems, such as fake review detection and malware classification, and analyze the limitations of existing ML-based malware classifiers proposed in academia and industry. Additionally, I investigate the threat of poisoning attacks against ML systems and propose three attacks: (1) Bullseye Polytope, a clean-label poisoning attack against transfer learning; (2) VenoMave, a poisoning attack against Automatic Speech Recognition; and (3) TrojanPuzzle, a poisoning attack against large language models of programming code.Overall, this dissertation contributes to a deeper understanding of the challenges and opportunities at the intersection of Machine Learning and Computer Security and offers insights into building more secure and resilient ML-based systems.

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

Mode of access: World Wide Web

ISBN: 9798380158336Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Computer SecurityIndex Terms--Genre/Form:

554714
Electronic books.

Machine Learning and Security in Adversarial Settings.
LDR:02814ntm a22003737 4500 001 1146393
005 20240812064604.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380158336
035 $a (MiAaPQ)AAI30522723
035 $a AAI30522723
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Aghakhani, Hojjat. $3 1471777
245 1 0 $a Machine Learning and Security in Adversarial Settings.
264 0 $c 2023
300 $a 1 online resource (251 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: 85-02, Section: B.
500 $a Advisor: Kruegel, Christopher;Vigna, Giovanni.
502 $a Thesis (Ph.D.)--University of California, Santa Barbara, 2023.
504 $a Includes bibliographical references
520 $a Recent advancements in Machine Learning (ML) and growing computing power have led to the increased use of ML-based systems in security-critical applications such as face recognition, fingerprint identification, and malware detection, as well as in high-stakes applications like autonomous driving. However, as these systems become more prevalent, it is crucial to consider their risks and limitations carefully and to develop robust and secure systems that can withstand attacks.In this dissertation, I employ theoretical analysis and empirical evaluation to advance the understanding at the intersection of Machine Learning and Computer Security. Specifically, I present novel ML-based approaches to address security-related problems, such as fake review detection and malware classification, and analyze the limitations of existing ML-based malware classifiers proposed in academia and industry. Additionally, I investigate the threat of poisoning attacks against ML systems and propose three attacks: (1) Bullseye Polytope, a clean-label poisoning attack against transfer learning; (2) VenoMave, a poisoning attack against Automatic Speech Recognition; and (3) TrojanPuzzle, a poisoning attack against large language models of programming code.Overall, this dissertation contributes to a deeper understanding of the challenges and opportunities at the intersection of Machine Learning and Computer Security and offers insights into building more secure and resilient ML-based systems.
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 Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a Computer Security
653 $a Machine Learning
653 $a Malware detection
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Santa Barbara. $b Computer Science. $3 1182528
773 0 $t Dissertations Abstracts International $g 85-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30522723 $z click for full text (PQDT)