본문

서브메뉴

Optimizing Privacy-Utility Trade-Offs in AI-Enabled Network Applications
Optimizing Privacy-Utility Trade-Offs in AI-Enabled Network Applications
Optimizing Privacy-Utility Trade-Offs in AI-Enabled Network Applications

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152757
ISBN  
9798383689325
DDC  
621.3
저자명  
Zhang, Jiang.
서명/저자  
Optimizing Privacy-Utility Trade-Offs in AI-Enabled Network Applications
발행사항  
[Sl] : University of Southern California, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
310 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
주기사항  
Advisor: Psounis, Konstantinos.
학위논문주기  
Thesis (Ph.D.)--University of Southern California, 2024.
초록/해제  
요약Over the past decade, Artificial Intelligence (AI) techniques have been widely used in various network applications, significantly enhancing the intelligence, efficiency, and personalization of the services provided for users. However, this advancement has intensified privacy concerns due to the development of Machine Learning (ML) models that learn from user data. Therefore, how to deliver high-quality and personalized online services using ML models while minimizing privacy risks for users has become a crucial research area.In this thesis, I develop innovative methods and systems to optimize the privacy-utility trade-offs in AI-enabled network applications. Recognizing that users face varied types of privacy risks across different applications, different privacy protection methods and systems tailored to address application-specific challenges are proposed. The thesis is organized into three main parts, detailed as follows.In the first part (Chapter 2-4), I focus on network applications in which the server collects user data and employs centralized learning methods to develop ML models from user data. To minimize the privacy leakage during the collection of user data while preserving the utility of ML models trained on such data, I propose methods to optimize user privacy and utility via data obfuscation (i.e. noise addition), aiming at protecting two common types of user privacy: user location privacy and user profiling privacy.In the second part (Chapter 5-6), I consider network applications using Federated Learning (FL) with Secure Aggregation (SA), where users share encrypted local model updates with the server without sending private local data, and the server can only observe the aggregated model update without accessing individual local model updates. While SA guarantees the privacy for the local model updates of users from the encrypted model updates, the aggregated model update may still leak the private information about user data. To systematically investigate the privacy and utility trade-offs in FL with SA, I use formal metrics including Mutual Information and Differential Privacy to quantify both on-average and worst-case privacy leakage in FL with SA. I demonstrate that the inherent randomness in aggregated model updates can be leveraged as noise to offer privacy protection for individual user's data without hurting model utility.For the first two parts, the methodology I utilize to optimize privacy-utility trade-offs can be summarized as adding noise smartly into user data to hide sensitive information. More recently, the emerging Generative Large Foundation Models (FMs) have showcased their superior capability of generating high-quality synthetic data. Therefore, in the last part of thesis (Chapter 7-8), I design approaches to leverage large FMs to protect user privacy and maintain utility in specialized ML model training. I demonstrate that the high-quality synthetic data generated by large FMs can be used to train accurate specialized ML models with minimal or no usage of real user data.
일반주제명  
Electrical engineering
일반주제명  
Computer science
키워드  
Machine Learning
키워드  
Privacy risks
키워드  
Trade-offs
키워드  
Utility
기타저자  
University of Southern California Electrical Engineering
기본자료저록  
Dissertations Abstracts International. 86-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163818
■00520250211152757
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798383689325
■035    ▼a(MiAaPQ)AAI31555950
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aZhang,  Jiang.
■24510▼aOptimizing  Privacy-Utility  Trade-Offs  in  AI-Enabled  Network  Applications
■260    ▼a[Sl]▼bUniversity  of  Southern  California▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a310  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-02,  Section:  B.
■500    ▼aAdvisor:  Psounis,  Konstantinos.
■5021  ▼aThesis  (Ph.D.)--University  of  Southern  California,  2024.
■520    ▼aOver  the  past  decade,  Artificial  Intelligence  (AI)  techniques  have  been  widely  used  in  various  network  applications,  significantly  enhancing  the  intelligence,  efficiency,  and  personalization  of  the  services  provided  for  users.  However,  this  advancement  has  intensified  privacy  concerns  due  to  the  development  of  Machine  Learning  (ML)  models  that  learn  from  user  data.  Therefore,  how  to  deliver  high-quality  and  personalized  online  services  using  ML  models  while  minimizing  privacy  risks  for  users  has  become  a  crucial  research  area.In  this  thesis,  I  develop  innovative  methods  and  systems  to  optimize  the  privacy-utility  trade-offs  in  AI-enabled  network  applications.  Recognizing  that  users  face  varied  types  of  privacy  risks  across  different  applications,  different  privacy  protection  methods  and  systems  tailored  to  address  application-specific  challenges  are  proposed.  The  thesis  is  organized  into  three  main  parts,  detailed  as  follows.In  the  first  part  (Chapter  2-4),  I  focus  on  network  applications  in  which  the  server  collects  user  data  and  employs  centralized  learning  methods  to  develop  ML  models  from  user  data.  To  minimize  the  privacy  leakage  during  the  collection  of  user  data  while  preserving  the  utility  of  ML  models  trained  on  such  data,  I  propose  methods  to  optimize  user  privacy  and  utility  via  data  obfuscation  (i.e.  noise  addition),  aiming  at  protecting  two  common  types  of  user  privacy:  user  location  privacy  and  user  profiling  privacy.In  the  second  part  (Chapter  5-6),  I  consider  network  applications  using  Federated  Learning  (FL)  with  Secure  Aggregation  (SA),  where  users  share  encrypted  local  model  updates  with  the  server  without  sending  private  local  data,  and  the  server  can  only  observe  the  aggregated  model  update  without  accessing  individual  local  model  updates.  While  SA  guarantees  the  privacy  for  the  local  model  updates  of  users  from  the  encrypted  model  updates,  the  aggregated  model  update  may  still  leak  the  private  information  about  user  data.  To  systematically  investigate  the  privacy  and  utility  trade-offs  in  FL  with  SA,  I  use  formal  metrics  including  Mutual  Information  and  Differential  Privacy  to  quantify  both  on-average  and  worst-case  privacy  leakage  in  FL  with  SA.  I  demonstrate  that  the  inherent  randomness  in  aggregated  model  updates  can  be  leveraged  as  noise  to  offer  privacy  protection  for  individual  user's  data  without  hurting  model  utility.For  the  first  two  parts,  the  methodology  I  utilize  to  optimize  privacy-utility  trade-offs  can  be  summarized  as  adding  noise  smartly  into  user  data  to  hide  sensitive  information.  More  recently,  the  emerging  Generative  Large  Foundation  Models  (FMs)  have  showcased  their  superior  capability  of  generating  high-quality  synthetic  data.  Therefore,  in  the  last  part  of  thesis  (Chapter  7-8),  I  design  approaches  to  leverage  large  FMs  to  protect  user  privacy  and  maintain  utility  in  specialized  ML  model  training.  I  demonstrate  that  the  high-quality  synthetic  data  generated  by  large  FMs  can  be  used  to  train  accurate  specialized  ML  models  with  minimal  or  no  usage  of  real  user  data.
■590    ▼aSchool  code:  0208.
■650  4▼aElectrical  engineering
■650  4▼aComputer  science
■653    ▼aMachine  Learning
■653    ▼aPrivacy  risks
■653    ▼aTrade-offs
■653    ▼aUtility
■690    ▼a0544
■690    ▼a0984
■690    ▼a0800
■71020▼aUniversity  of  Southern  California▼bElectrical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-02B.
■790    ▼a0208
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163818▼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
    TF11086 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.