서브메뉴
검색
Toward Managing Catastrophic AI Risks
Toward Managing Catastrophic AI Risks
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105702
- ISBN
- 9798263308056
- DDC
- 004
- 저자명
- Mazeika, Mantas.
- 서명/저자
- Toward Managing Catastrophic AI Risks
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 224 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Forsyth, David.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
- 초록/해제
- 요약Artificial intelligence (AI) has rapidly improved over the past decade, leading to widespread adoption of AI systems and demonstrating the potential for AI to greatly benefit society. However, as with any powerful new technology, AI introduces risks that must be managed to fully realize these benefits. Recent breakthroughs in the generality of AI systems have drawn increased attention to AI risks, including those of a potentially catastrophic nature. To help manage these anticipated risks, we take a defense in depth approach, combining different areas of AI safety research to address different aspects of AI risk. We present research on making AI systems more robust to adversarial influence, monitoring AIs for hidden behavior and trojans, enabling AIs to understand and adhere to human values, and finally addressing systemic problems to enable increased transparency.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 일반주제명
- Information technology
- 키워드
- AI safety
- 키워드
- Red teaming
- 키워드
- Neural trojans
- 키워드
- Trojan detection
- 키워드
- Alignment
- 키워드
- Model stealing
- 기타저자
- University of Illinois at Urbana-Champaign Computer Science
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2024 us c eng d■001000017361077
■00520260202105702
■006m o d
■007cr#unu||||||||
■020 ▼a9798263308056
■035 ▼a(MiAaPQ)AAI32409887
■035 ▼a(MiAaPQ)124375
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aMazeika, Mantas.
■24510▼aToward Managing Catastrophic AI Risks
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a224 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Forsyth, David.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
■520 ▼aArtificial intelligence (AI) has rapidly improved over the past decade, leading to widespread adoption of AI systems and demonstrating the potential for AI to greatly benefit society. However, as with any powerful new technology, AI introduces risks that must be managed to fully realize these benefits. Recent breakthroughs in the generality of AI systems have drawn increased attention to AI risks, including those of a potentially catastrophic nature. To help manage these anticipated risks, we take a defense in depth approach, combining different areas of AI safety research to address different aspects of AI risk. We present research on making AI systems more robust to adversarial influence, monitoring AIs for hidden behavior and trojans, enabling AIs to understand and adhere to human values, and finally addressing systemic problems to enable increased transparency.
■590 ▼aSchool code: 0090.
■650 4▼aComputer science
■650 4▼aComputer engineering
■650 4▼aInformation technology
■653 ▼aAI safety
■653 ▼aRed teaming
■653 ▼aNeural trojans
■653 ▼aTrojan detection
■653 ▼aAlignment
■653 ▼aModel stealing
■690 ▼a0800
■690 ▼a0984
■690 ▼a0489
■690 ▼a0464
■71020▼aUniversity of Illinois at Urbana-Champaign▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361077▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
