서브메뉴
검색
Customized Robustness for Machine Learning Models
Customized Robustness for Machine Learning Models
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104837
- ISBN
- 9798291590508
- DDC
- 004
- 저자명
- Lin, Weiran.
- 서명/저자
- Customized Robustness for Machine Learning Models
- 발행사항
- [Sl] : Carnegie Mellon University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 173 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: A.
- 주기사항
- Advisor: Bauer, Lujo.
- 학위논문주기
- Thesis (Ph.D.)--Carnegie Mellon University, 2025.
- 초록/해제
- 요약Evasion attacks perturb inputs of machine-learning models to induce undesired behaviors. Existing metrics commonly evaluate the risks of evasion attacks by untargeted robustness, and these metrics do not correspond to many practical adversarial goals. As a mitigation, we propose customized robustness, a general framework of robustness definitions that corresponds to specific use cases. With such a framework, we identify new definitions of robustness that remain unexplored by existing work, including but not limited to robustness that involves multiple input or output instances and robustness that involves multiple models. We further explore new threat models with these novel definitions, and invent new metrics that better capture the risks. Our new definitions also motivate stronger and more efficient tools to assess robustness in many real world use cases, including various loss functions that more accurately capture adversary goals.
- 일반주제명
- Computer science
- 일반주제명
- Communication
- 일반주제명
- Information technology
- 키워드
- Existing metrics
- 키워드
- Evasion attacks
- 키워드
- Robustness
- 기타저자
- Carnegie Mellon University Electrical and Computer Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-03A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359119
■00520260202104837
■006m o d
■007cr#unu||||||||
■020 ▼a9798291590508
■035 ▼a(MiAaPQ)AAI32171832
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aLin, Weiran.
■24510▼aCustomized Robustness for Machine Learning Models
■260 ▼a[Sl]▼bCarnegie Mellon University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a173 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: A.
■500 ▼aAdvisor: Bauer, Lujo.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2025.
■520 ▼aEvasion attacks perturb inputs of machine-learning models to induce undesired behaviors. Existing metrics commonly evaluate the risks of evasion attacks by untargeted robustness, and these metrics do not correspond to many practical adversarial goals. As a mitigation, we propose customized robustness, a general framework of robustness definitions that corresponds to specific use cases. With such a framework, we identify new definitions of robustness that remain unexplored by existing work, including but not limited to robustness that involves multiple input or output instances and robustness that involves multiple models. We further explore new threat models with these novel definitions, and invent new metrics that better capture the risks. Our new definitions also motivate stronger and more efficient tools to assess robustness in many real world use cases, including various loss functions that more accurately capture adversary goals.
■590 ▼aSchool code: 0041.
■650 4▼aComputer science
■650 4▼aCommunication
■650 4▼aInformation technology
■653 ▼aExisting metrics
■653 ▼aEvasion attacks
■653 ▼aMachine-learning models
■653 ▼aRobustness
■690 ▼a0984
■690 ▼a0489
■690 ▼a0459
■690 ▼a0800
■71020▼aCarnegie Mellon University▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g87-03A.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359119▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
