본문

서브메뉴

Adversarial Resilient and Privacy Preserving Deep Learning
Adversarial Resilient and Privacy Preserving Deep Learning
Adversarial Resilient and Privacy Preserving Deep Learning

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105542
ISBN  
9798263397852
DDC  
006
저자명  
Wei, Wenqi.
서명/저자  
Adversarial Resilient and Privacy Preserving Deep Learning
발행사항  
[Sl] : Georgia Institute of Technology, 2022
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2022
형태사항  
332 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Liu, Ling.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2022.
초록/해제  
요약Deep learning is being deployed in the cloud and on edge devices for a wide range of domain-specific applications, ranging from healthcare, cyber-manufacturing, autonomic vehicles, to smart cities and smart planet initiatives. While deep learning creates new opportunities for business, engineering, and scientific discoveries, it also introduces new attack surfaces to the modern computing systems that incorporate deep learning as a core component for algorithmic decision making and cognitive machine intelligence, ranging from data poisoning and model inversion during the training phase and adversarial evasion attacks during model inference phase, aiming to cause the well-trained model to misbehave randomly or purposefully. This dissertation research addresses these problems with dual focuses: First, it aims to provide a fundamental understanding of the security and privacy vulnerabilities inherent in deep neural network training and inference. Second, it develops an adversarial resilient framework and a set of optimization techniques to safeguard the deep learning systems, services, and applications against adversarial manipulations and gradient leakage induced privacy violations, while maintaining the accuracy and convergence performance of deep learning systems. This dissertation research has made three unique contributions towards advancing the knowledge and technological foundation for privacy-preserving deep learning with adversarial robustness against deceptions.The first main contribution is an in-depth investigation into security and privacy threats inherent in deep learning, represented by gradient leakage attacks during both centralized and distributed training, model manipulation with data poisoning during model training, and deception queries to well-trained models at the inference phase, represented by adversarial examples and out-of-distribution inputs. By introducing a principled approach to investigating gradient leakage attacks and different attack optimization methods in both centralized model training and federated learning environments, we provide a comprehensive risk assessment framework for an in-depth analysis of different attack mechanisms and attack surfaces that an adversary may leverage to reconstruct the private training data. Similarly, we take a holistic approach to creating an in-depth understanding of both adversarial examples and out-of-distribution examples in terms of their adversarial transferability and their inherent divergence. We also present a comprehensive study on the data poisoning to reveal its effectiveness and robust statistics under the complication scenarios of federated learning. Our research exposes the root causes for these adversarial vulnerabilities and provides transformative enlightenment on designing mitigation strategies and effective countermeasures.The second main contribution of this dissertation is to develop a cross-layer strategic ensemble verification methodology (XEnsemble) for enhancing the adversarial robustness of DNN model inference in the presence of adversarial examples and out-of-distribution examples. XEnsemble by design has three unique capabilities. (i) XEnsemble builds diverse input denoising verifiers by leveraging different data cleaning techniques. (ii) XEnsemble develops a disagreement-diversity ensemble learning methodology for guarding the output of the prediction model against deception. (iii) XEnsemble provides a suite of algorithms to combine input verification and output verification to protect the DNN prediction models from both adversarial examples and out-of-distribution inputs.The third contribution is the development of gradient leakage attack resilient deep learning for both centralized model training and distributed model training systems with privacy enhancing optimizations. To circumvent gradient leakage attacks, we investigate different strategies to add noise to the intermediate model parameter updates during model training (centralized or federated learning) with dual optimization goals: (i) the amount of noise added should be sufficient to remove the privacy leakages of private training data, and (ii) the amount of noise added should not be too much to hurt the overall accuracy and convergence of the trained model. We provide a theoretical formalization to certify the robustness provided differential privacy noise injection against gradient leakage attack. We also extend the conventional deep learning with differential privacy approach with the fixed privacy parameters for DP controlled noise injection by introducing adaptive privacy parameters to both centralized deep learning with differential privacy and federated deep learning with differential privacy.
일반주제명  
Deep learning
일반주제명  
Privacy
일반주제명  
Defense
일반주제명  
Impact analysis
일반주제명  
Deception
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2022        us                              c    eng  d
■001000017360532
■00520260202105542
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263397852
■035    ▼a(MiAaPQ)AAI32315294
■035    ▼a(MiAaPQ)GeorgiaTech72437
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a006
■1001  ▼aWei,  Wenqi.
■24510▼aAdversarial  Resilient  and  Privacy  Preserving  Deep  Learning
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2022
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2022
■300    ▼a332  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Liu,  Ling.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2022.
■520    ▼aDeep  learning  is  being  deployed  in  the  cloud  and  on  edge  devices  for  a  wide  range  of  domain-specific  applications,  ranging  from  healthcare,  cyber-manufacturing,  autonomic  vehicles,  to  smart  cities  and  smart  planet  initiatives.  While  deep  learning  creates  new  opportunities  for  business,  engineering,  and  scientific  discoveries,  it  also  introduces  new  attack  surfaces  to  the  modern  computing  systems  that  incorporate  deep  learning  as  a  core  component  for  algorithmic  decision  making  and  cognitive  machine  intelligence,  ranging  from  data  poisoning  and  model  inversion  during  the  training  phase  and  adversarial  evasion  attacks  during  model  inference  phase,  aiming  to  cause  the  well-trained  model  to  misbehave  randomly  or  purposefully.  This  dissertation  research  addresses  these  problems  with  dual  focuses:  First,  it  aims  to  provide  a  fundamental  understanding  of  the  security  and  privacy  vulnerabilities  inherent  in  deep  neural  network  training  and  inference.  Second,  it  develops  an  adversarial  resilient  framework  and  a  set  of  optimization  techniques  to  safeguard  the  deep  learning  systems,  services,  and  applications  against  adversarial  manipulations  and  gradient  leakage  induced  privacy  violations,  while  maintaining  the  accuracy  and  convergence  performance  of  deep  learning  systems.  This  dissertation  research  has  made  three  unique  contributions  towards  advancing  the  knowledge  and  technological  foundation  for  privacy-preserving  deep  learning  with  adversarial  robustness  against  deceptions.The  first  main  contribution  is  an  in-depth  investigation  into  security  and  privacy  threats  inherent  in  deep  learning,  represented  by  gradient  leakage  attacks  during  both  centralized  and  distributed  training,  model  manipulation  with  data  poisoning  during  model  training,  and  deception  queries  to  well-trained  models  at  the  inference  phase,  represented  by  adversarial  examples  and  out-of-distribution  inputs.  By  introducing  a  principled  approach  to  investigating  gradient  leakage  attacks  and  different  attack  optimization  methods  in  both  centralized  model  training  and  federated  learning  environments,  we  provide  a  comprehensive  risk  assessment  framework  for  an  in-depth  analysis  of  different  attack  mechanisms  and  attack  surfaces  that  an  adversary  may  leverage  to  reconstruct  the  private  training  data.  Similarly,  we  take  a  holistic  approach  to  creating  an  in-depth  understanding  of  both  adversarial  examples  and  out-of-distribution  examples  in  terms  of  their  adversarial  transferability  and  their  inherent  divergence.  We  also  present  a  comprehensive  study  on  the  data  poisoning  to  reveal  its  effectiveness  and  robust  statistics  under  the  complication  scenarios  of  federated  learning.  Our  research  exposes  the  root  causes  for  these  adversarial  vulnerabilities  and  provides  transformative  enlightenment  on  designing  mitigation  strategies  and  effective  countermeasures.The  second  main  contribution  of  this  dissertation  is  to  develop  a  cross-layer  strategic  ensemble  verification  methodology  (XEnsemble)  for  enhancing  the  adversarial  robustness  of  DNN  model  inference  in  the  presence  of  adversarial  examples  and  out-of-distribution  examples.  XEnsemble  by  design  has  three  unique  capabilities.  (i)  XEnsemble  builds  diverse  input  denoising  verifiers  by  leveraging  different  data  cleaning  techniques.  (ii)  XEnsemble  develops  a  disagreement-diversity  ensemble  learning  methodology  for  guarding  the  output  of  the  prediction  model  against  deception.  (iii)  XEnsemble  provides  a  suite  of  algorithms  to  combine  input  verification  and  output  verification  to  protect  the  DNN  prediction  models  from  both  adversarial  examples  and  out-of-distribution  inputs.The  third  contribution  is  the  development  of  gradient  leakage  attack  resilient  deep  learning  for  both  centralized  model  training  and  distributed  model  training  systems  with  privacy  enhancing  optimizations.  To  circumvent  gradient  leakage  attacks,  we  investigate  different  strategies  to  add  noise  to  the  intermediate  model  parameter  updates  during  model  training  (centralized  or  federated  learning)  with  dual  optimization  goals:  (i)  the  amount  of  noise  added  should  be  sufficient  to  remove  the  privacy  leakages  of  private  training  data,  and  (ii)  the  amount  of  noise  added  should  not  be  too  much  to  hurt  the  overall  accuracy  and  convergence  of  the  trained  model.  We  provide  a  theoretical  formalization  to  certify  the  robustness  provided  differential  privacy  noise  injection  against  gradient  leakage  attack.  We  also  extend  the  conventional  deep  learning  with  differential  privacy  approach  with  the  fixed  privacy  parameters  for  DP  controlled  noise  injection  by  introducing  adaptive  privacy  parameters  to  both  centralized  deep  learning  with  differential  privacy  and  federated  deep  learning  with  differential  privacy.
■590    ▼aSchool  code:  0078.
■650  4▼aDeep  learning
■650  4▼aPrivacy
■650  4▼aDefense
■650  4▼aImpact  analysis
■650  4▼aDeception
■690    ▼a0800
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2022
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360532▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF14787 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.