본문

서브메뉴

Securing Deep Reinforcement Learning
Securing Deep Reinforcement Learning
Securing Deep Reinforcement Learning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152937
ISBN  
9798346856788
DDC  
004
저자명  
Wu, Xian.
서명/저자  
Securing Deep Reinforcement Learning
발행사항  
[Sl] : Northwestern University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
163 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
주기사항  
Advisor: Xing, Xinyu.
학위논문주기  
Thesis (Ph.D.)--Northwestern University, 2024.
초록/해제  
요약Deep reinforcement learning (DRL) has shown remarkable potential in various applications, including video game playing, mastering the game of Go, and autonomous piloting. Despite these successes, DRL systems are vulnerable to adversarial attacks, where adversaries can manipulate a well-trained agent's behavior by altering the input to the policy network or by training adversarial agents to exploit the victim's weaknesses. The latter type of attack, which involves adversarial agents, is more realistic and challenging to counteract compared to observation perturbations. Existing work on defending against this type of attack has not demonstrated high exploitability in complex games, nor has it provided effective defense strategies.In this dissertation, I tackle the challenge of adversarial agent attacks by proposing a comprehensive system that integrates explainable AI, optimization, adversarial training, and game theory. This system is designed to detect, expose, and correct flaws in DRL policies by developing adversarial agents that engage with target agents to reveal and mitigate their vulnerabilities. Moreover, I enhance our understanding of adversarial policies by modeling attacks and defenses as a two-player zero-sum game and propose a novel, provably effective defense. Specifically, I first present a novel method for training adversarial agent which utilize the explainable AI techniques to effectively exploit the weakness of the victim agent. Following that, I introduce another optimization-based adversarial training algorithm with stronger exploitability and better transferability. Additionally, I explore potential defenses using these adversarial training methods. Beyond adversarial policies, I develop a provable defense against adversarial agent attacks within two-player competitive games. This dissertation research realizes a systematic framework for adversarial agent attacks and defenses in deep reinforcement learning. By utilizing this framework, we can significantly enhance the security of deep reinforcement learning applications.
일반주제명  
Computer science
키워드  
Adversarial attack
키워드  
Provable defense
키워드  
Reinforcement learning
기타저자  
Northwestern University Computer Science
기본자료저록  
Dissertations Abstracts International. 86-06B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164235
■00520250211152937
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346856788
■035    ▼a(MiAaPQ)AAI31563833
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aWu,  Xian.
■24510▼aSecuring  Deep  Reinforcement  Learning
■260    ▼a[Sl]▼bNorthwestern  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a163  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-06,  Section:  B.
■500    ▼aAdvisor:  Xing,  Xinyu.
■5021  ▼aThesis  (Ph.D.)--Northwestern  University,  2024.
■520    ▼aDeep  reinforcement  learning  (DRL)  has  shown  remarkable  potential  in  various  applications,  including  video  game  playing,  mastering  the  game  of  Go,  and  autonomous  piloting.  Despite  these  successes,  DRL  systems  are  vulnerable  to  adversarial  attacks,  where  adversaries  can  manipulate  a  well-trained  agent's  behavior  by  altering  the  input  to  the  policy  network  or  by  training  adversarial  agents  to  exploit  the  victim's  weaknesses.  The  latter  type  of  attack,  which  involves  adversarial  agents,  is  more  realistic  and  challenging  to  counteract  compared  to  observation  perturbations.  Existing  work  on  defending  against  this  type  of  attack  has  not  demonstrated  high  exploitability  in  complex  games,  nor  has  it  provided  effective  defense  strategies.In  this  dissertation,  I  tackle  the  challenge  of  adversarial  agent  attacks  by  proposing  a  comprehensive  system  that  integrates  explainable  AI,  optimization,  adversarial  training,  and  game  theory.  This  system  is  designed  to  detect,  expose,  and  correct  flaws  in  DRL  policies  by  developing  adversarial  agents  that  engage  with  target  agents  to  reveal  and  mitigate  their  vulnerabilities.  Moreover,  I  enhance  our  understanding  of  adversarial  policies  by  modeling  attacks  and  defenses  as  a  two-player  zero-sum  game  and  propose  a  novel,  provably  effective  defense.  Specifically,  I  first  present  a  novel  method  for  training  adversarial  agent  which  utilize  the  explainable  AI  techniques  to  effectively  exploit  the  weakness  of  the  victim  agent.  Following  that,  I  introduce  another  optimization-based  adversarial  training  algorithm  with  stronger  exploitability  and  better  transferability.  Additionally,  I  explore  potential  defenses  using  these  adversarial  training  methods.  Beyond  adversarial  policies,  I  develop  a  provable  defense  against  adversarial  agent  attacks  within  two-player  competitive  games.  This  dissertation  research  realizes  a  systematic  framework  for  adversarial  agent  attacks  and  defenses  in  deep  reinforcement  learning.  By  utilizing  this  framework,  we  can  significantly  enhance  the  security  of  deep  reinforcement  learning  applications.
■590    ▼aSchool  code:  0163.
■650  4▼aComputer  science
■653    ▼aAdversarial  attack
■653    ▼aProvable  defense
■653    ▼aReinforcement  learning
■690    ▼a0984
■690    ▼a0800
■71020▼aNorthwestern  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g86-06B.
■790    ▼a0163
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164235▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF10157 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.