서브메뉴
검색
Trustworthy Binary Classifications in Dynamic Systems Under Uncertainty
Trustworthy Binary Classifications in Dynamic Systems Under Uncertainty
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105509
- ISBN
- 9798263328924
- DDC
- 004
- 저자명
- Kumar, Harshit.
- 서명/저자
- Trustworthy Binary Classifications in Dynamic Systems Under Uncertainty
- 발행사항
- [Sl] : Georgia Institute of Technology, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 133 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Mukhopadhyay, Saibal.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2024.
- 초록/해제
- 요약Binary classifications are commonly used in modeling dynamic systems and are prevalent in machine learning and deep learning applications. These classifications directly inform decision-making, however, uncertainty in modeling can undermine prediction trustworthiness. This dissertation aims to enhance binary classification reliability in dynamic systems under various uncertainties, focusing on safety-critical applications like malware detection and wildfire prediction. In these contexts, predictions inform critical mitigation decisions, necessitating high-fidelity predictions across a range of behaviors that dynamic systems are likely to exhibit. To achieve this, we identify different sources of uncertainty in the modeling pipeline and propose mitigative measures.In malware detection, we perform online uncertainty estimation to monitor predictions post-deployment, recognizing the model's limitations in classifying unknown behavior as benign or malicious. Next, we develop strategies to faithfully capture malware behavior, reducing or managing uncertainty that manifests as an overlap between the positive and negative classes. Finally, shifting the context to a complex dynamic system like wildfire evolution, we address irreducible uncertainty arising from the system's inherent randomness. Here, we propose a novel evaluation criterion that treats uncertainty as a feature rather than a bug. This criterion tests the model's ability to capture macro system behaviors and does not penalize the model if it accurately learns the system's inherent uncertainty.We consolidate our learnings into an uncertainty-based framework which can be used for designing reliable data-driven models that perform binary classifications in uncertain dynamic environments. Our findings apply to alert generation using time series and spatiotemporal data collected from sensors monitoring dynamic system behavior.
- 일반주제명
- Stochastic models
- 일반주제명
- Malware
- 일반주제명
- Telemetry
- 일반주제명
- Decision making
- 일반주제명
- Computer science
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2024 us c eng d■001000017360337
■00520260202105509
■006m o d
■007cr#unu||||||||
■020 ▼a9798263328924
■035 ▼a(MiAaPQ)AAI32308083
■035 ▼a(MiAaPQ)GeorgiaTech78608
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aKumar, Harshit.
■24510▼aTrustworthy Binary Classifications in Dynamic Systems Under Uncertainty
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a133 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Mukhopadhyay, Saibal.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2024.
■520 ▼aBinary classifications are commonly used in modeling dynamic systems and are prevalent in machine learning and deep learning applications. These classifications directly inform decision-making, however, uncertainty in modeling can undermine prediction trustworthiness. This dissertation aims to enhance binary classification reliability in dynamic systems under various uncertainties, focusing on safety-critical applications like malware detection and wildfire prediction. In these contexts, predictions inform critical mitigation decisions, necessitating high-fidelity predictions across a range of behaviors that dynamic systems are likely to exhibit. To achieve this, we identify different sources of uncertainty in the modeling pipeline and propose mitigative measures.In malware detection, we perform online uncertainty estimation to monitor predictions post-deployment, recognizing the model's limitations in classifying unknown behavior as benign or malicious. Next, we develop strategies to faithfully capture malware behavior, reducing or managing uncertainty that manifests as an overlap between the positive and negative classes. Finally, shifting the context to a complex dynamic system like wildfire evolution, we address irreducible uncertainty arising from the system's inherent randomness. Here, we propose a novel evaluation criterion that treats uncertainty as a feature rather than a bug. This criterion tests the model's ability to capture macro system behaviors and does not penalize the model if it accurately learns the system's inherent uncertainty.We consolidate our learnings into an uncertainty-based framework which can be used for designing reliable data-driven models that perform binary classifications in uncertain dynamic environments. Our findings apply to alert generation using time series and spatiotemporal data collected from sensors monitoring dynamic system behavior.
■590 ▼aSchool code: 0078.
■650 4▼aStochastic models
■650 4▼aMalware
■650 4▼aTelemetry
■650 4▼aDecision making
■650 4▼aComputer science
■690 ▼a0800
■690 ▼a0984
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360337▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
