본문

서브메뉴

A Perturbation Approach to Differential Privacy for Deep Learning Based Speech Processing
A Perturbation Approach to Differential Privacy for Deep Learning Based Speech Processing
A Perturbation Approach to Differential Privacy for Deep Learning Based Speech Processing

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260209102908
ISBN  
9798263393823
DDC  
004
저자명  
Yang, Chao-Han.
서명/저자  
A Perturbation Approach to Differential Privacy for Deep Learning Based Speech Processing
발행사항  
[Sl] : Georgia Institute of Technology, 2023
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2023
형태사항  
135 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Lee, Chin-Hui.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
초록/해제  
요약Speech signals contain rich information that encompasses the characteristics of speakers and speaking environments. To deploy high-performance speech applications, deep neural network (DNN) based models are widely utilized and trained with speech data. However, the training set often contains personal information that needs to be protected. New data regulations (e.g., GDPR) require service providers to ensure necessary privacy protections through privacy measurements to avoid security threats from query-based malicious attacks. Differential privacy (DP) is a technique that provides identity protection with a mathematical definition for measuring privacy losses under query-based attacks. DP is built upon randomization processes for identity anonymization by setting up a privacy budget (溝). However, ensuring DP in DNN models often leads to a severe performance loss due to the data perturbation process for achieving a strong privacy budget.This dissertation aims to establish a perturbation-based learning framework for training with DNNs to maintain the high performance of speech models while satisfying DP requirements. We develop specific mechanisms for signal distortion by adding bounded noise to the speech training data. These perturbations can be analyzed through statistical measurements and estimations of the deployed models. Our theoretical studies have used both Laplace and Gaussian noise to guarantee the 溝 privacy budget under a bounded maxdivergence measurement with ensemble learning. We further leverage upon the properties of Lipchitz continuity of DNNs to provide model robustness estimation under different 溝 budgets. Speech recognition in both isolated speech commands and large vocabulary continuous speech settings has been utilized to corroborate our theorems.We have advanced the proposed framework into popular speech and acoustic modeling tasks and conducted preliminary investigations to explore the trade-off between ensemble model performance and DP budgets. Our findings show that even with state-of-the-art speaker anonymization techniques, speaker identity information can still be leaked without DP-based data extraction or training methods. Finally, we have incorporated decentralized and federated training pipelines of deep neural networks (DNNs) into the proposed privacypreserving speech processing mechanism to investigate potential solutions for on-device or cloud-based speech applications for end-users.
일반주제명  
Data integrity
일반주제명  
Privacy
일반주제명  
Neural networks
일반주제명  
Computer science
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260203s2023        us                              c    eng  d
■001000017365983
■00520260209102908
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263393823
■035    ▼a(MiAaPQ)AAI32315763
■035    ▼a(MiAaPQ)GeorgiaTech75094
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aYang,  Chao-Han.
■24512▼aA  Perturbation  Approach  to  Differential  Privacy  for  Deep  Learning  Based  Speech  Processing
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a135  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Lee,  Chin-Hui.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2023.
■520    ▼aSpeech  signals  contain  rich  information  that  encompasses  the  characteristics  of  speakers  and  speaking  environments.  To  deploy  high-performance  speech  applications,  deep  neural  network  (DNN)  based  models  are  widely  utilized  and  trained  with  speech  data.  However,  the  training  set  often  contains  personal  information  that  needs  to  be  protected.  New  data  regulations  (e.g.,  GDPR)  require  service  providers  to  ensure  necessary  privacy  protections  through  privacy  measurements  to  avoid  security  threats  from  query-based  malicious  attacks.  Differential  privacy  (DP)  is  a  technique  that  provides  identity  protection  with  a  mathematical  definition  for  measuring  privacy  losses  under  query-based  attacks.  DP  is  built  upon  randomization  processes  for  identity  anonymization  by  setting  up  a  privacy  budget  (溝).  However,  ensuring  DP  in  DNN  models  often  leads  to  a  severe  performance  loss  due  to  the  data  perturbation  process  for  achieving  a  strong  privacy  budget.This  dissertation  aims  to  establish  a  perturbation-based  learning  framework  for  training  with  DNNs  to  maintain  the  high  performance  of  speech  models  while  satisfying  DP  requirements.  We  develop  specific  mechanisms  for  signal  distortion  by  adding  bounded  noise  to  the  speech  training  data.  These  perturbations  can  be  analyzed  through  statistical  measurements  and  estimations  of  the  deployed  models.  Our  theoretical  studies  have  used  both  Laplace  and  Gaussian  noise  to  guarantee  the  溝  privacy  budget  under  a  bounded  maxdivergence  measurement  with  ensemble  learning.  We  further  leverage  upon  the  properties  of  Lipchitz  continuity  of  DNNs  to  provide  model  robustness  estimation  under  different  溝  budgets.  Speech  recognition  in  both  isolated  speech  commands  and  large  vocabulary  continuous  speech  settings  has  been  utilized  to  corroborate  our  theorems.We  have  advanced  the  proposed  framework  into  popular  speech  and  acoustic  modeling  tasks  and  conducted  preliminary  investigations  to  explore  the  trade-off  between  ensemble  model  performance  and  DP  budgets.  Our  findings  show  that  even  with  state-of-the-art  speaker  anonymization  techniques,  speaker  identity  information  can  still  be  leaked  without  DP-based  data  extraction  or  training  methods.  Finally,  we  have  incorporated  decentralized  and  federated  training  pipelines  of  deep  neural  networks  (DNNs)  into  the  proposed  privacypreserving  speech  processing  mechanism  to  investigate  potential  solutions  for  on-device  or  cloud-based  speech  applications  for  end-users.
■590    ▼aSchool  code:  0078.
■650  4▼aData  integrity
■650  4▼aPrivacy
■650  4▼aNeural  networks
■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    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365983▼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
    TF15944 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.