본문

서브메뉴

Automatically Improving the Code Quality of Rust Via LLM
Automatically Improving the Code Quality of Rust Via LLM
Automatically Improving the Code Quality of Rust Via LLM

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105503
ISBN  
9798263324704
DDC  
658
저자명  
Cheng, Xiang.
서명/저자  
Automatically Improving the Code Quality of Rust Via LLM
발행사항  
[Sl] : Georgia Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
121 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Kim, Taesoo.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
초록/해제  
요약Ensuring the quality and safety of Rust code is increasingly critical as the language is adopted for system-level and security-sensitive applications. The unique features of Rust, such as its ownership and borrowing system, present both opportunities and challenges for automated code quality improvement. This work addresses these challenges by leveraging LLMs in three key areas: automatic unit test generation, detection of unsafe operations in binaries, and identification of logically unsafe operations that escape compiler checks.The research introduces a comprehensive framework that integrates semantic-aware static analysis with advanced machine learning techniques tailored for Rust's complex type system. The first component, RUG, employs a bottom-up context construction strategy and coverage-guided fuzzing to generate high-quality unit tests, achieving coverage rates comparable to human developers. The second component, RUBY, applies machine learning to identify unsafe operations directly in Rust binaries, enabling security analysis even when source code is unavailable. The third component, COIN, uses LLM-based classification and proof-of-concept generation to uncover logically unsafe operations, revealing vulnerabilities that are not detected by the compiler.Extensive evaluation across thousands of real-world Rust projects demonstrates the effectiveness of these approaches, with significant improvements in code coverage, precision, and recall over existing tools. The results highlight the potential of LLMs, when combined with domain-specific program analysis, to address the unique challenges of Rust and advance the state of automated code quality assurance.
일반주제명  
Behavior
일반주제명  
Software
일반주제명  
Programming languages
일반주제명  
Large language models
일반주제명  
Semantics
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360298
■00520260202105503
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263324704
■035    ▼a(MiAaPQ)AAI32307958
■035    ▼a(MiAaPQ)GeorgiaTech78728
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a658
■1001  ▼aCheng,  Xiang.
■24510▼aAutomatically  Improving  the  Code  Quality  of  Rust  Via  LLM
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a121  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Kim,  Taesoo.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2025.
■520    ▼aEnsuring  the  quality  and  safety  of  Rust  code  is  increasingly  critical  as  the  language  is  adopted  for  system-level  and  security-sensitive  applications.  The  unique  features  of  Rust,  such  as  its  ownership  and  borrowing  system,  present  both  opportunities  and  challenges  for  automated  code  quality  improvement.  This  work  addresses  these  challenges  by  leveraging  LLMs  in  three  key  areas:  automatic  unit  test  generation,  detection  of  unsafe  operations  in  binaries,  and  identification  of  logically  unsafe  operations  that  escape  compiler  checks.The  research  introduces  a  comprehensive  framework  that  integrates  semantic-aware  static  analysis  with  advanced  machine  learning  techniques  tailored  for  Rust's  complex  type  system.  The  first  component,  RUG,  employs  a  bottom-up  context  construction  strategy  and  coverage-guided  fuzzing  to  generate  high-quality  unit  tests,  achieving  coverage  rates  comparable  to  human  developers.  The  second  component,  RUBY,  applies  machine  learning  to  identify  unsafe  operations  directly  in  Rust  binaries,  enabling  security  analysis  even  when  source  code  is  unavailable.  The  third  component,  COIN,  uses  LLM-based  classification  and  proof-of-concept  generation  to  uncover  logically  unsafe  operations,  revealing  vulnerabilities  that  are  not  detected  by  the  compiler.Extensive  evaluation  across  thousands  of  real-world  Rust  projects  demonstrates  the  effectiveness  of  these  approaches,  with  significant  improvements  in  code  coverage,  precision,  and  recall  over  existing  tools.  The  results  highlight  the  potential  of  LLMs,  when  combined  with  domain-specific  program  analysis,  to  address  the  unique  challenges  of  Rust  and  advance  the  state  of  automated  code  quality  assurance.
■590    ▼aSchool  code:  0078.
■650  4▼aBehavior
■650  4▼aSoftware
■650  4▼aProgramming  languages
■650  4▼aLarge  language  models
■650  4▼aSemantics
■690    ▼a0800
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360298▼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
    TF18966 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.