A Machine-Learning Algorithm with Disjunctive Model for Data-Driven Program Analysis
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeon, Minseok | - |
dc.contributor.author | Jeong, Sehun | - |
dc.contributor.author | Cha, Sungdeok | - |
dc.contributor.author | Oh, Hakjoo | - |
dc.date.accessioned | 2021-09-01T14:40:54Z | - |
dc.date.available | 2021-09-01T14:40:54Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-06 | - |
dc.identifier.issn | 0164-0925 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/65304 | - |
dc.description.abstract | We present a new machine-learning algorithm with disjunctive model for data-driven program analysis. One major challenge in static program analysis is a substantial amount of manual effort required for tuning the analysis performance. Recently, data-driven program analysis has emerged to address this challenge by automatically adjusting the analysis based on data through a learning algorithm. Although this new approach has proven promising for various program analysis tasks, its effectiveness has been limited due to simple-minded learning models and algorithms that are unable to capture sophisticated, in particular disjunctive, program properties. To overcome this shortcoming, this article presents a new disjunctive model for data-driven program analysis as well as a learning algorithm to find the model parameters. Our model uses Boolean formulas over atomic features and therefore is able to express nonlinear combinations of program properties. A key technical challenge is to efficiently determine a set of good Boolean formulas, as brute-force search would simply be impractical. We present a stepwise and greedy algorithm that efficiently learns Boolean formulas. We show the effectiveness and generality of our algorithm with two static analyzers: context-sensitive points-to analysis for Java and flow-sensitive interval analysis for C. Experimental results show that our automated technique significantly improves the performance of the state-of-the-art techniques including ones hand-crafted by human experts. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ASSOC COMPUTING MACHINERY | - |
dc.subject | POINTS-TO ANALYSIS | - |
dc.subject | CONTEXT-SENSITIVITY | - |
dc.subject | STRATEGY | - |
dc.subject | PRECISE | - |
dc.subject | OCTAGON | - |
dc.title | A Machine-Learning Algorithm with Disjunctive Model for Data-Driven Program Analysis | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Cha, Sungdeok | - |
dc.contributor.affiliatedAuthor | Oh, Hakjoo | - |
dc.identifier.doi | 10.1145/3293607 | - |
dc.identifier.scopusid | 2-s2.0-85075699476 | - |
dc.identifier.wosid | 000501220300007 | - |
dc.identifier.bibliographicCitation | ACM TRANSACTIONS ON PROGRAMMING LANGUAGES AND SYSTEMS, v.41, no.2 | - |
dc.relation.isPartOf | ACM TRANSACTIONS ON PROGRAMMING LANGUAGES AND SYSTEMS | - |
dc.citation.title | ACM TRANSACTIONS ON PROGRAMMING LANGUAGES AND SYSTEMS | - |
dc.citation.volume | 41 | - |
dc.citation.number | 2 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.subject.keywordPlus | POINTS-TO ANALYSIS | - |
dc.subject.keywordPlus | CONTEXT-SENSITIVITY | - |
dc.subject.keywordPlus | STRATEGY | - |
dc.subject.keywordPlus | PRECISE | - |
dc.subject.keywordPlus | OCTAGON | - |
dc.subject.keywordAuthor | Data-driven program analysis | - |
dc.subject.keywordAuthor | static analysis | - |
dc.subject.keywordAuthor | context-sensitivity | - |
dc.subject.keywordAuthor | flow-sensitivity | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.