JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism

Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identificati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Jin, Huang, Zishan, Xiao, Hui, Xiao, Yinhao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Wang, Jin
Huang, Zishan
Xiao, Hui
Xiao, Yinhao
description Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.
doi_str_mv 10.48550/arxiv.2307.15915
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2307_15915</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307_15915</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-15627e50e415fba71a2f58141b995373952f6f7517bdaa59d45faa11fadff8d43</originalsourceid><addsrcrecordid>eNotkM1Og0AURtm4MNUHcOV9AZABLgPusLHapv7Fxi25MHfsJHQww0Dat6-trr7FSb7knCC4EXGUFYjxHbm9maIkjWUksBR4GexXC2MVu3uo4LWfuIPKtVvjufWjY9C9gxVNBF9jZ9lRYzrjD7BUbL3RpiVvegsPNLCCj5EUfHKnw8r7E_8lZBW8Ow69I2ON_YYXbrdkzbC7Ci40dQNf_-8s2CweN_PncP32tJxX65ByiaHAPJGMMWcCdUNSUKKxEJloyhJTmZaY6FxLFLJRRFiqDDWREJqU1oXK0llw-3d7Vq9_nNmRO9SnBPU5QXoEbiVX2w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism</title><source>arXiv.org</source><creator>Wang, Jin ; Huang, Zishan ; Xiao, Hui ; Xiao, Yinhao</creator><creatorcontrib>Wang, Jin ; Huang, Zishan ; Xiao, Hui ; Xiao, Yinhao</creatorcontrib><description>Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.</description><identifier>DOI: 10.48550/arxiv.2307.15915</identifier><language>eng</language><subject>Computer Science - Cryptography and Security</subject><creationdate>2023-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2307.15915$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2307.15915$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Jin</creatorcontrib><creatorcontrib>Huang, Zishan</creatorcontrib><creatorcontrib>Xiao, Hui</creatorcontrib><creatorcontrib>Xiao, Yinhao</creatorcontrib><title>JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism</title><description>Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.</description><subject>Computer Science - Cryptography and Security</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkM1Og0AURtm4MNUHcOV9AZABLgPusLHapv7Fxi25MHfsJHQww0Dat6-trr7FSb7knCC4EXGUFYjxHbm9maIkjWUksBR4GexXC2MVu3uo4LWfuIPKtVvjufWjY9C9gxVNBF9jZ9lRYzrjD7BUbL3RpiVvegsPNLCCj5EUfHKnw8r7E_8lZBW8Ow69I2ON_YYXbrdkzbC7Ci40dQNf_-8s2CweN_PncP32tJxX65ByiaHAPJGMMWcCdUNSUKKxEJloyhJTmZaY6FxLFLJRRFiqDDWREJqU1oXK0llw-3d7Vq9_nNmRO9SnBPU5QXoEbiVX2w</recordid><startdate>20230729</startdate><enddate>20230729</enddate><creator>Wang, Jin</creator><creator>Huang, Zishan</creator><creator>Xiao, Hui</creator><creator>Xiao, Yinhao</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230729</creationdate><title>JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism</title><author>Wang, Jin ; Huang, Zishan ; Xiao, Hui ; Xiao, Yinhao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-15627e50e415fba71a2f58141b995373952f6f7517bdaa59d45faa11fadff8d43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Cryptography and Security</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Jin</creatorcontrib><creatorcontrib>Huang, Zishan</creatorcontrib><creatorcontrib>Xiao, Hui</creatorcontrib><creatorcontrib>Xiao, Yinhao</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wang, Jin</au><au>Huang, Zishan</au><au>Xiao, Hui</au><au>Xiao, Yinhao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism</atitle><date>2023-07-29</date><risdate>2023</risdate><abstract>Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.</abstract><doi>10.48550/arxiv.2307.15915</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2307.15915
ispartof
issn
language eng
recordid cdi_arxiv_primary_2307_15915
source arXiv.org
subjects Computer Science - Cryptography and Security
title JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T19%3A42%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=JFinder:%20A%20Novel%20Architecture%20for%20Java%20Vulnerability%20Identification%20Based%20Quad%20Self-Attention%20and%20Pre-training%20Mechanism&rft.au=Wang,%20Jin&rft.date=2023-07-29&rft_id=info:doi/10.48550/arxiv.2307.15915&rft_dat=%3Carxiv_GOX%3E2307_15915%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true