서브메뉴
검색
Certifiably Trustworthy Deep Learning Systems at Scale
Certifiably Trustworthy Deep Learning Systems at Scale
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102856
- ISBN
- 9798291574300
- DDC
- 004
- 저자명
- Li, Linyi.
- 서명/저자
- Certifiably Trustworthy Deep Learning Systems at Scale
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 547 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
- 주기사항
- Advisor: Li, Bo;Xie, Tao.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
- 초록/해제
- 요약Great advances in deep learning (DL) have led to state-of-the-art performance on a wide range of challenging tasks. However, along with the rapid deployment of DL systems, several trustworthy threats arise, such as weak robustness against stealthy noise perturbations and natural transformations, bias across different subgroups, and lack of numerical reliability. These trustworthy threats have raised great concerns, especially when deploying DL systems in safety-critical scenarios such as autonomous driving and facial recognition for safeguarding. To defend against these common trustworthy threats, this thesis systematically proposes or enhances certification approaches and certified training approaches for DL systems, especially for large-scale DL systems.A certification approach can guarantee some properties of the DL system under some trustworthiness properties. For instance, the robustness certification approach can guarantee the worst-case test accuracy when the attacker imposes any input perturbations or transformations within some bounded range. A certified training approach can improve the DL system's guaranteed trustworthiness under a certain property by training the DL model, e.g., improving the guaranteed test accuracy above.This thesis begins with a systematic taxonomy of certification and certified training approaches. Then for several critical trustworthiness properties, this thesis proposes the corresponding certification and certified training approaches that lead to state-of-the-art tightness and scalability. These approaches are motivated by a few core principles, including dual problem analysis for randomized smoothing, general cutting planes for bound propagation, stratified sampling, subpopulation decomposition, and abstract interpretation. The effectiveness of the proposed approaches is supported by both theoretical analyses and empirical evaluations. The thesis is concluded with a discussion of limitations, challenges, and future directions towards achieving fully certifiable, reliable, and scalable machine learning.In summary, this thesis enables certification of various trustworthy properties for DL systems up to millions of parameters, representing a major step in certified deep learning, an important research topic in machine learning, computer security, and software engineering.
- 일반주제명
- Computer science
- 일반주제명
- Information technology
- 일반주제명
- Robotics
- 키워드
- Deep learning
- 키워드
- Certification
- 키워드
- Verification
- 기타저자
- University of Illinois at Urbana-Champaign Computer Science
- 기본자료저록
- Dissertations Abstracts International. 87-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365923
■00520260209102856
■006m o d
■007cr#unu||||||||
■020 ▼a9798291574300
■035 ▼a(MiAaPQ)AAI32272137
■035 ▼a(MiAaPQ)httphdlhandlenet2142121953
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aLi, Linyi.
■24510▼aCertifiably Trustworthy Deep Learning Systems at Scale
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a547 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: B.
■500 ▼aAdvisor: Li, Bo;Xie, Tao.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
■520 ▼aGreat advances in deep learning (DL) have led to state-of-the-art performance on a wide range of challenging tasks. However, along with the rapid deployment of DL systems, several trustworthy threats arise, such as weak robustness against stealthy noise perturbations and natural transformations, bias across different subgroups, and lack of numerical reliability. These trustworthy threats have raised great concerns, especially when deploying DL systems in safety-critical scenarios such as autonomous driving and facial recognition for safeguarding. To defend against these common trustworthy threats, this thesis systematically proposes or enhances certification approaches and certified training approaches for DL systems, especially for large-scale DL systems.A certification approach can guarantee some properties of the DL system under some trustworthiness properties. For instance, the robustness certification approach can guarantee the worst-case test accuracy when the attacker imposes any input perturbations or transformations within some bounded range. A certified training approach can improve the DL system's guaranteed trustworthiness under a certain property by training the DL model, e.g., improving the guaranteed test accuracy above.This thesis begins with a systematic taxonomy of certification and certified training approaches. Then for several critical trustworthiness properties, this thesis proposes the corresponding certification and certified training approaches that lead to state-of-the-art tightness and scalability. These approaches are motivated by a few core principles, including dual problem analysis for randomized smoothing, general cutting planes for bound propagation, stratified sampling, subpopulation decomposition, and abstract interpretation. The effectiveness of the proposed approaches is supported by both theoretical analyses and empirical evaluations. The thesis is concluded with a discussion of limitations, challenges, and future directions towards achieving fully certifiable, reliable, and scalable machine learning.In summary, this thesis enables certification of various trustworthy properties for DL systems up to millions of parameters, representing a major step in certified deep learning, an important research topic in machine learning, computer security, and software engineering.
■590 ▼aSchool code: 0090.
■650 4▼aComputer science
■650 4▼aInformation technology
■650 4▼aRobotics
■653 ▼aDeep learning
■653 ▼aCertification
■653 ▼aVerification
■653 ▼aTrustworthy machine learning
■653 ▼aMachine learning security
■690 ▼a0984
■690 ▼a0800
■690 ▼a0489
■690 ▼a0771
■71020▼aUniversity of Illinois at Urbana-Champaign▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g87-02B.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365923▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


