본문

서브메뉴

Towards Secure and Robust 3K Perception in the Real World: An Adversarial Approach
Towards Secure and Robust 3K Perception in the Real World: An Adversarial Approach
Towards Secure and Robust 3K Perception in the Real World: An Adversarial Approach

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152751
ISBN  
9798342117197
DDC  
629.13252
저자명  
Cheng, Zhiyuan.
서명/저자  
Towards Secure and Robust 3K Perception in the Real World: An Adversarial Approach
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
198 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Zhang, Xiangyu;Celik, Z. Berkay;Li, Pan;Zhang, Tianyi.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약The advent of advanced machine learning and computer vision techniques has led to the feasibility of 3D perception in the real world, which includes but not limited to tasks of monocular depth estimation (MDE), 3D object detection, semantic scene completion, optical flow estimation (OFE), etc. Due to the 3D nature of our physical world, these techniques have enabled various real-world applications like Autonomous Driving (AD), unmanned aerial vehicle (UAV), virtual/augmented reality (VR/AR) and video composition, revolutionizing the field of transportation and entertainment. However, it is well-documented that Deep Neural Network (DNN) models can be susceptible to adversarial attacks. These attacks, characterized by minimal perturbations, can precipitate substantial malfunctions. Considering that 3D perception techniques are crucial for security-sensitive applications, such as autonomous driving systems (ADS), in the real world, adversarial attacks on these systems represent significant threats. As a result, my goal of research is to build secure and robust real-world 3D perception systems.Through the examination of vulnerabilities in 3D perception techniques under such attacks, my dissertation aims to expose and mitigate these weaknesses. Specifically, I propose stealthy physical-world attacks against MDE, a fundamental component in ADS and AR/VR that facilitates the projection from 2D to 3D. I have advanced the stealth of the patch attack by minimizing the patch size and disguising the adversarial pattern, striking an optimal balance between stealth and efficacy. Moreover, I develop single-modal attacks against camera-LiDAR fusion models for 3D object detection, utilizing adversarial patches. This method underscores that mere fusion of sensors does not assure robustness against adversarial attacks. Additionally, I study black-box attacks against MDE and OFE models, which are more practical and impactful as no model details are required and the models can be compromised through only queries. In parallel, I devise a self-supervised adversarial training method to harden MDE models without the necessity of ground-truth depth labels. This enhanced model is capable of withstanding a range of adversarial attacks, including those in the physical world. Through these innovative designs for both attack and defense, this research contributes to the development of more secure and robust 3D perception systems, particularly in the context of the real world applications.
일반주제명  
Unmanned aerial vehicles
일반주제명  
Autonomous vehicles
일반주제명  
Neural networks
일반주제명  
Aerospace engineering
일반주제명  
Robotics
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163775
■00520250211152751
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342117197
■035    ▼a(MiAaPQ)AAI31532249
■035    ▼a(MiAaPQ)Purdue26254682
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.13252
■1001  ▼aCheng,  Zhiyuan.
■24510▼aTowards  Secure  and  Robust  3K  Perception  in  the  Real  World:  An  Adversarial  Approach
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a198  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Zhang,  Xiangyu;Celik,  Z.  Berkay;Li,  Pan;Zhang,  Tianyi.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼aThe  advent  of  advanced  machine  learning  and  computer  vision  techniques  has  led  to  the  feasibility  of  3D  perception  in  the  real  world,  which  includes  but  not  limited  to  tasks  of  monocular  depth  estimation  (MDE),  3D  object  detection,  semantic  scene  completion,  optical  flow  estimation  (OFE),  etc.  Due  to  the  3D  nature  of  our  physical  world,  these  techniques  have  enabled  various  real-world  applications  like  Autonomous  Driving  (AD),  unmanned  aerial  vehicle  (UAV),  virtual/augmented  reality  (VR/AR)  and  video  composition,  revolutionizing  the  field  of  transportation  and  entertainment.  However,  it  is  well-documented  that  Deep  Neural  Network  (DNN)  models  can  be  susceptible  to  adversarial  attacks.  These  attacks,  characterized  by  minimal  perturbations,  can  precipitate  substantial  malfunctions.  Considering  that  3D  perception  techniques  are  crucial  for  security-sensitive  applications,  such  as  autonomous  driving  systems  (ADS),  in  the  real  world,  adversarial  attacks  on  these  systems  represent  significant  threats.  As  a  result,  my  goal  of  research  is  to  build  secure  and  robust  real-world  3D  perception  systems.Through  the  examination  of  vulnerabilities  in  3D  perception  techniques  under  such  attacks,  my  dissertation  aims  to  expose  and  mitigate  these  weaknesses.  Specifically,  I  propose  stealthy  physical-world  attacks  against  MDE,  a  fundamental  component  in  ADS  and  AR/VR  that  facilitates  the  projection  from  2D  to  3D.  I  have  advanced  the  stealth  of  the  patch  attack  by  minimizing  the  patch  size  and  disguising  the  adversarial  pattern,  striking  an  optimal  balance  between  stealth  and  efficacy.  Moreover,  I  develop  single-modal  attacks  against  camera-LiDAR  fusion  models  for  3D  object  detection,  utilizing  adversarial  patches.  This  method  underscores  that  mere  fusion  of  sensors  does  not  assure  robustness  against  adversarial  attacks.  Additionally,  I  study  black-box  attacks  against  MDE  and  OFE  models,  which  are  more  practical  and  impactful  as  no  model  details  are  required  and  the  models  can  be  compromised  through  only  queries.  In  parallel,  I  devise  a  self-supervised  adversarial  training  method  to  harden  MDE  models  without  the  necessity  of  ground-truth  depth  labels.  This  enhanced  model  is  capable  of  withstanding  a  range  of  adversarial  attacks,  including  those  in  the  physical  world.  Through  these  innovative  designs  for  both  attack  and  defense,  this  research  contributes  to  the  development  of  more  secure  and  robust  3D  perception  systems,  particularly  in  the  context  of  the  real  world  applications.
■590    ▼aSchool  code:  0183.
■650  4▼aUnmanned  aerial  vehicles
■650  4▼aAutonomous  vehicles
■650  4▼aNeural  networks
■650  4▼aAerospace  engineering
■650  4▼aRobotics
■690    ▼a0800
■690    ▼a0538
■690    ▼a0771
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163775▼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
    TF09798 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.