BGNN4VD: Constructing Bidirectional Graph Neural-Network for Vulnerability Detection

Previous studies have shown that existing deep learning-based approaches can significantly improve the performance of vulnerability detection. They represent code in various forms and mine vulnerability features with deep learning models. However, the differences of code representation forms and dee...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information and software technology Jg. 136; S. 106576
Hauptverfasser: Cao, Sicong, Sun, Xiaobing, Bo, Lili, Wei, Ying, Li, Bin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.08.2021
Schlagworte:
ISSN:0950-5849, 1873-6025
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Previous studies have shown that existing deep learning-based approaches can significantly improve the performance of vulnerability detection. They represent code in various forms and mine vulnerability features with deep learning models. However, the differences of code representation forms and deep learning models make various approaches still have some limitations. In practice, their false-positive rate (FPR) and false-negative rate (FNR) are still high. To address the limitations of existing deep learning-based vulnerability detection approaches, we propose BGNN4VD (Bidirectional Graph Neural Network for Vulnerability Detection), a vulnerability detection approach by constructing a Bidirectional Graph Neural-Network (BGNN). In Phase 1, we extract the syntax and semantic information of source code through abstract syntax tree (AST), control flow graph (CFG), and data flow graph (DFG). Then in Phase 2, we use vectorized source code as input to Bidirectional Graph Neural-Network (BGNN). In Phase 3, we learn the different features between vulnerable code and non-vulnerable code by introducing backward edges on the basis of traditional Graph Neural-Network (GNN). Finally in Phase 4, a Convolutional Neural-Network (CNN) is used to further extract features and detect vulnerabilities through a classifier. We evaluate BGNN4VD on four popular C/C++ projects from NVD and GitHub, and compare it with four state-of-the-art (Flawfinder, RATS, SySeVR, and VUDDY) vulnerab ility detection approaches. Experiment results show that, when compared these baselines, BGNN4VD achieves 4.9%, 11.0%, and 8.4% improvement in F1-measure, accuracy and precision, respectively. The proposed BGNN4VD achieves a higher precision and accuracy than the state-of-the-art methods. In addition, when applied on the latest vulnerabilities reported by CVE, BGNN4VD can still achieve a precision at 45.1%, which demonstrates the feasibility of BGNN4VD in practical application.
AbstractList Previous studies have shown that existing deep learning-based approaches can significantly improve the performance of vulnerability detection. They represent code in various forms and mine vulnerability features with deep learning models. However, the differences of code representation forms and deep learning models make various approaches still have some limitations. In practice, their false-positive rate (FPR) and false-negative rate (FNR) are still high. To address the limitations of existing deep learning-based vulnerability detection approaches, we propose BGNN4VD (Bidirectional Graph Neural Network for Vulnerability Detection), a vulnerability detection approach by constructing a Bidirectional Graph Neural-Network (BGNN). In Phase 1, we extract the syntax and semantic information of source code through abstract syntax tree (AST), control flow graph (CFG), and data flow graph (DFG). Then in Phase 2, we use vectorized source code as input to Bidirectional Graph Neural-Network (BGNN). In Phase 3, we learn the different features between vulnerable code and non-vulnerable code by introducing backward edges on the basis of traditional Graph Neural-Network (GNN). Finally in Phase 4, a Convolutional Neural-Network (CNN) is used to further extract features and detect vulnerabilities through a classifier. We evaluate BGNN4VD on four popular C/C++ projects from NVD and GitHub, and compare it with four state-of-the-art (Flawfinder, RATS, SySeVR, and VUDDY) vulnerab ility detection approaches. Experiment results show that, when compared these baselines, BGNN4VD achieves 4.9%, 11.0%, and 8.4% improvement in F1-measure, accuracy and precision, respectively. The proposed BGNN4VD achieves a higher precision and accuracy than the state-of-the-art methods. In addition, when applied on the latest vulnerabilities reported by CVE, BGNN4VD can still achieve a precision at 45.1%, which demonstrates the feasibility of BGNN4VD in practical application.
ArticleNumber 106576
Author Wei, Ying
Li, Bin
Sun, Xiaobing
Bo, Lili
Cao, Sicong
Author_xml – sequence: 1
  givenname: Sicong
  surname: Cao
  fullname: Cao, Sicong
  organization: School of Information Engineering, Yangzhou University, Yangzhou, China
– sequence: 2
  givenname: Xiaobing
  orcidid: 0000-0001-5165-5080
  surname: Sun
  fullname: Sun, Xiaobing
  email: xbsun@yzu.edu.cn
  organization: School of Information Engineering, Yangzhou University, Yangzhou, China
– sequence: 3
  givenname: Lili
  surname: Bo
  fullname: Bo, Lili
  organization: School of Information Engineering, Yangzhou University, Yangzhou, China
– sequence: 4
  givenname: Ying
  surname: Wei
  fullname: Wei, Ying
  organization: School of Information Engineering, Yangzhou University, Yangzhou, China
– sequence: 5
  givenname: Bin
  surname: Li
  fullname: Li, Bin
  email: lb@yzu.edu.cn
  organization: School of Information Engineering, Yangzhou University, Yangzhou, China
BookMark eNqFkMtOwzAQRS1UJNrCH7DID6SM83CSLpBoCwWpCpvSreU4Y3AJdmW7oP49rcKKBazmaqRzNXNGZGCsQUKuKUwoUHaznWijvFWTBBJ6XLG8YGdkSMsijRkk-YAMocohzsusuiAj77cAtIAUhmQ9W9Z1tllMo7k1Pri9DNq8RjPdaofHbI3ooqUTu7eoxr0TXVxj-LLuPVLWRZt9Z9CJRnc6HKIFhh65JOdKdB6vfuaYvDzcr-eP8ep5-TS_W8UyBRZiZFXZVAKgkBLLsmUsU2WKaYN5nsoqqxKa0SaHiuWQFa1AkUloEqUEolLYpmMy7Xuls947VFzqIE4XBCd0xynwkx--5b0ffvLDez9HOPsF75z-EO7wH3bbY3h87FOj415qNBJ7Yby1-u-CbxgYhQE
CitedBy_id crossref_primary_10_1109_TSE_2023_3285910
crossref_primary_10_1016_j_cose_2023_103341
crossref_primary_10_1016_j_infsof_2025_107826
crossref_primary_10_1145_3721977
crossref_primary_10_1016_j_cose_2023_103501
crossref_primary_10_1186_s13638_023_02242_7
crossref_primary_10_1007_s10664_023_10319_6
crossref_primary_10_1145_3699711
crossref_primary_10_1145_3694782
crossref_primary_10_3390_aerospace10050465
crossref_primary_10_3390_e24050651
crossref_primary_10_1109_JIOT_2023_3294496
crossref_primary_10_1002_smr_2508
crossref_primary_10_1145_3712190
crossref_primary_10_3390_s22093577
crossref_primary_10_1016_j_cose_2025_104548
crossref_primary_10_1155_2022_4875859
crossref_primary_10_1016_j_future_2024_107671
crossref_primary_10_1016_j_cose_2022_102823
crossref_primary_10_1016_j_cose_2024_103992
crossref_primary_10_1016_j_jss_2024_112031
crossref_primary_10_1016_j_cose_2024_103994
crossref_primary_10_1002_smr_70026
crossref_primary_10_1016_j_jss_2025_112459
crossref_primary_10_1016_j_jss_2024_112038
crossref_primary_10_1016_j_infsof_2023_107168
crossref_primary_10_1016_j_infsof_2024_107544
crossref_primary_10_32604_cmc_2023_029135
crossref_primary_10_1145_3763230
crossref_primary_10_1109_ACCESS_2022_3191115
crossref_primary_10_1016_j_infsof_2025_107722
crossref_primary_10_1016_j_jss_2023_111775
crossref_primary_10_1109_ACCESS_2024_3467180
crossref_primary_10_1016_j_infsof_2023_107371
crossref_primary_10_3390_app15126524
crossref_primary_10_1016_j_cose_2024_103930
crossref_primary_10_1016_j_infsof_2025_107739
crossref_primary_10_32604_cmc_2024_049310
crossref_primary_10_1109_TII_2024_3413305
crossref_primary_10_1109_MC_2022_3228924
crossref_primary_10_1007_s00521_022_08046_y
crossref_primary_10_1016_j_cose_2022_102915
crossref_primary_10_1049_sfw2_12066
crossref_primary_10_1109_TR_2023_3319318
crossref_primary_10_1016_j_infsof_2024_107566
crossref_primary_10_1016_j_scico_2024_103156
crossref_primary_10_1016_j_jss_2023_111706
crossref_primary_10_1088_1674_1056_acb9fa
crossref_primary_10_1109_ACCESS_2023_3338162
crossref_primary_10_1016_j_jss_2023_111705
crossref_primary_10_1016_j_cose_2024_103787
crossref_primary_10_1016_j_future_2024_107504
crossref_primary_10_1007_s00500_022_07777_3
crossref_primary_10_1109_ACCESS_2024_3378533
crossref_primary_10_1109_ACCESS_2023_3309850
crossref_primary_10_1007_s10664_022_10216_4
crossref_primary_10_1016_j_ins_2024_121370
crossref_primary_10_1016_j_cose_2025_104350
crossref_primary_10_3390_electronics11091334
crossref_primary_10_1016_j_jss_2023_111832
crossref_primary_10_32604_cmc_2024_050281
crossref_primary_10_1109_TSE_2022_3147265
crossref_primary_10_1155_2022_1919907
crossref_primary_10_3390_s25061816
crossref_primary_10_3390_math12101447
crossref_primary_10_26634_jse_17_4_19813
crossref_primary_10_1093_comjnl_bxaf094
crossref_primary_10_1145_3624744
crossref_primary_10_1016_j_infsof_2024_107581
crossref_primary_10_1145_3640333
crossref_primary_10_1016_j_cose_2024_104139
crossref_primary_10_1016_j_infsof_2024_107406
crossref_primary_10_1007_s10515_025_00532_6
crossref_primary_10_3390_jcp1040035
crossref_primary_10_1016_j_cose_2024_104098
crossref_primary_10_1016_j_jss_2025_112581
crossref_primary_10_1155_2021_9997641
crossref_primary_10_1016_j_asoc_2025_113057
crossref_primary_10_3390_electronics13245007
crossref_primary_10_1109_TKDE_2023_3333371
crossref_primary_10_1016_j_infsof_2025_107893
crossref_primary_10_1142_S0218194025500408
crossref_primary_10_1007_s13042_023_01824_7
crossref_primary_10_1016_j_infsof_2024_107517
crossref_primary_10_1016_j_cose_2024_103732
crossref_primary_10_1016_j_infsof_2023_107219
crossref_primary_10_1016_j_hcc_2024_100268
crossref_primary_10_1109_ACCESS_2022_3216395
crossref_primary_10_1186_s42400_024_00245_5
crossref_primary_10_1016_j_jss_2025_112595
crossref_primary_10_1109_JIOT_2024_3381641
crossref_primary_10_1016_j_cose_2024_104024
crossref_primary_10_3390_s24217089
crossref_primary_10_3103_S0146411623080126
crossref_primary_10_1016_j_eswa_2023_121865
crossref_primary_10_1007_s42979_025_03777_w
crossref_primary_10_1109_MITP_2023_3284628
Cites_doi 10.1109/TSE.2005.112
10.1007/s10664-016-9447-3
10.1109/TSE.2011.103
10.1145/3276517
10.1016/j.jss.2020.110659
10.1016/j.jss.2020.110538
10.1007/s11432-017-9459-5
10.1016/j.infsof.2013.02.009
10.1109/TSE.2017.2659751
10.1109/TSE.2010.81
10.1016/j.infsof.2019.07.003
10.1007/s10664-018-9661-2
ContentType Journal Article
Copyright 2021
Copyright_xml – notice: 2021
DBID AAYXX
CITATION
DOI 10.1016/j.infsof.2021.106576
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Business
EISSN 1873-6025
ExternalDocumentID 10_1016_j_infsof_2021_106576
S0950584921000586
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29I
4.4
457
4G.
5GY
5VS
7-5
71M
77K
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
AAYOK
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACGOD
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
AEBSH
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BKOMP
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
KOM
LG9
M41
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSV
SSZ
T5K
TWZ
UHS
UNMZH
WH7
WUQ
XFK
ZY4
~G-
77I
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-e698b9a007cce88d664f83e3be553c9492141b50965047daea4c0b2ffaeeffed3
ISICitedReferencesCount 152
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000655363900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0950-5849
IngestDate Tue Nov 18 22:45:15 EST 2025
Sat Nov 29 07:06:23 EST 2025
Fri Feb 23 02:42:37 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Bidirectional Graph Neural-Network
Code representation
Vulnerability detection
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-e698b9a007cce88d664f83e3be553c9492141b50965047daea4c0b2ffaeeffed3
ORCID 0000-0001-5165-5080
ParticipantIDs crossref_citationtrail_10_1016_j_infsof_2021_106576
crossref_primary_10_1016_j_infsof_2021_106576
elsevier_sciencedirect_doi_10_1016_j_infsof_2021_106576
PublicationCentury 2000
PublicationDate August 2021
2021-08-00
PublicationDateYYYYMMDD 2021-08-01
PublicationDate_xml – month: 08
  year: 2021
  text: August 2021
PublicationDecade 2020
PublicationTitle Information and software technology
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Gascon, Yamaguchi, Arp, Rieck (b36) 2013
Abadi, Barham, Chen, Chen, Davis, Dean, Devin, Ghemawat, Irving, Isard, Kudlur, Levenberg, Monga, Moore, Murray, Steiner, Tucker, Vasudevan, Warden, Wicke, Yu, Zheng (b38) 2016
Xu, Li, Deng, Chen (b14) 2018
Zhou, Sun, Xia, Li, Chen (b21) 2019; 114
Huang, Xia, Lo (b26) 2019; 24
Li, Zou, Xu, Ou, Jin, Wang, Deng, Zhong (b27) 2018
Munaiah, Camilo, Wigham, Meneely, Nagappan (b3) 2017; 22
Boudjema, Verlan, Mokdad, Faure (b11) 2020; 3
Yuan, Lu, Wang, Xue (b15) 2014
Dam, Tran, Pham, Ng, Grundy, Ghose (b31) 2017
Yi, Yang, Guo, Wang, Liu, Zhao (b12) 2018; 44
Gyimóthy, Ferenc, Siket (b22) 2005; 31
Zhang, Zheng, Zou, Hassan (b25) 2016
Zheng, Gao, Wu, Liu, Xun, Liu, Chen (b40) 2020; 168
Zhuang, Liu, Qian, Liu, Wang, He (b2) 2020
Xu, Xu, Chen, Song, Liu, Liu (b17) 2020
Zhang, Cui, Neumann, Chen (b41) 2018
Li, Zou, Xu, Jin, Zhu, Chen, Wang, Wang (b28) 2018
Radjenovic, Hericko, Torkar, Zivkovic (b24) 2013; 55
Shin, Meneely, Williams, Osborne (b6) 2011; 37
Ni, Li, Sun, Chen, Tang, Shi (b8) 2020; 163
Baxter, Yahin, de Moura, Sant’Anna, Bier (b34) 1998
Kipf, Welling (b37) 2017
Yamaguchi, Lottmann, Rieck (b7) 2012
Liu, Jin, Xu, Bu, Zou, Zhang (b18) 2019
Sun, Peng, Zhang, Liu, Cai (b1) 2019; 62
Guo, Li, Yin, Gao (b13) 2019; vol. 11999
Nam, Kim (b20) 2015
Wu, Wang, Liu, Wang (b29) 2017
Russell, Kim, Hamilton, Lazovich, Harer, Ozdemir, Ellingwood, McConley (b30) 2018
Li, Tarlow, Brockschmidt, Zemel (b33) 2016
Drozd, Wagner (b10) 2018
Xu, Chen, Chandramohan, Liu, Song (b19) 2017
Pradel, Sen (b42) 2018; 2
Kingma, Ba (b39) 2015
Kim, Woo, Lee, Oh (b5) 2017
Zhou, Liu, Siow, Du, Liu (b32) 2019
Sparks, Embleton, Cunningham, Zou (b35) 2007
Liu, Shen, Zhu, Niu, Li, Zhang (b16) 2020
Hall, Beecham, Bowes, Gray, Counsell (b23) 2012; 38
Younis, Malaiya, Anderson, Ray (b43) 2016
Jiang, Liu, Jiang, Zhang, Mei (b9) 2020
Du, Chen, Li, Guo, Zhou, Liu, Jiang (b4) 2019
Yuan (10.1016/j.infsof.2021.106576_b15) 2014
Sparks (10.1016/j.infsof.2021.106576_b35) 2007
Yi (10.1016/j.infsof.2021.106576_b12) 2018; 44
Li (10.1016/j.infsof.2021.106576_b33) 2016
Zhou (10.1016/j.infsof.2021.106576_b32) 2019
Xu (10.1016/j.infsof.2021.106576_b17) 2020
Ni (10.1016/j.infsof.2021.106576_b8) 2020; 163
Gyimóthy (10.1016/j.infsof.2021.106576_b22) 2005; 31
Gascon (10.1016/j.infsof.2021.106576_b36) 2013
Zheng (10.1016/j.infsof.2021.106576_b40) 2020; 168
Li (10.1016/j.infsof.2021.106576_b28) 2018
Younis (10.1016/j.infsof.2021.106576_b43) 2016
Abadi (10.1016/j.infsof.2021.106576_b38) 2016
Liu (10.1016/j.infsof.2021.106576_b16) 2020
Liu (10.1016/j.infsof.2021.106576_b18) 2019
Hall (10.1016/j.infsof.2021.106576_b23) 2012; 38
Zhang (10.1016/j.infsof.2021.106576_b25) 2016
Guo (10.1016/j.infsof.2021.106576_b13) 2019; vol. 11999
Shin (10.1016/j.infsof.2021.106576_b6) 2011; 37
Jiang (10.1016/j.infsof.2021.106576_b9) 2020
Zhuang (10.1016/j.infsof.2021.106576_b2) 2020
Drozd (10.1016/j.infsof.2021.106576_b10) 2018
Kingma (10.1016/j.infsof.2021.106576_b39) 2015
Yamaguchi (10.1016/j.infsof.2021.106576_b7) 2012
Zhou (10.1016/j.infsof.2021.106576_b21) 2019; 114
Boudjema (10.1016/j.infsof.2021.106576_b11) 2020; 3
Zhang (10.1016/j.infsof.2021.106576_b41) 2018
Dam (10.1016/j.infsof.2021.106576_b31) 2017
Kipf (10.1016/j.infsof.2021.106576_b37) 2017
Russell (10.1016/j.infsof.2021.106576_b30) 2018
Munaiah (10.1016/j.infsof.2021.106576_b3) 2017; 22
Li (10.1016/j.infsof.2021.106576_b27) 2018
Sun (10.1016/j.infsof.2021.106576_b1) 2019; 62
Pradel (10.1016/j.infsof.2021.106576_b42) 2018; 2
Huang (10.1016/j.infsof.2021.106576_b26) 2019; 24
Nam (10.1016/j.infsof.2021.106576_b20) 2015
Xu (10.1016/j.infsof.2021.106576_b19) 2017
Kim (10.1016/j.infsof.2021.106576_b5) 2017
Radjenovic (10.1016/j.infsof.2021.106576_b24) 2013; 55
Du (10.1016/j.infsof.2021.106576_b4) 2019
Wu (10.1016/j.infsof.2021.106576_b29) 2017
Xu (10.1016/j.infsof.2021.106576_b14) 2018
Baxter (10.1016/j.infsof.2021.106576_b34) 1998
References_xml – start-page: 1
  year: 2020
  ident: b16
  article-title: Deep learning based program generation from requirements text: Are we there yet?
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 462
  year: 2017
  end-page: 472
  ident: b19
  article-title: SPAIN: security patch analysis for binaries towards understanding the pain and pills
  publication-title: Proceedings of the 39th International Conference on Software Engineering, ICSE 2017, Buenos Aires, Argentina, May 20-28, 2017
– start-page: 368
  year: 1998
  end-page: 377
  ident: b34
  article-title: Clone detection using abstract syntax trees
  publication-title: 1998 International Conference on Software Maintenance, ICSM 1998, Bethesda, Maryland, USA, November 16-19, 1998
– start-page: 1
  year: 2019
  ident: b18
  article-title: Deep learning based code smell detection
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 595
  year: 2017
  end-page: 614
  ident: b5
  article-title: VUDDY: a scalable approach for vulnerable code clone discovery
  publication-title: 2017 IEEE Symposium on Security and Privacy, SP 2017, San Jose, CA, USA, May 22-26, 2017
– volume: 114
  start-page: 204
  year: 2019
  end-page: 216
  ident: b21
  article-title: Improving defect prediction with deep forest
  publication-title: Inf. Softw. Technol.
– start-page: 473
  year: 2018
  end-page: 487
  ident: b14
  article-title: Deeprefiner: Multi-layer android malware detection system applying deep neural networks
  publication-title: 2018 IEEE European Symposium on Security and Privacy, EuroS&P 2018, London, United Kingdom, April 24-26, 2018
– volume: 2
  start-page: 147:1
  year: 2018
  end-page: 147:25
  ident: b42
  article-title: Deepbugs: a learning approach to name-based bug detection
  publication-title: Proc. ACM Program. Lang.
– start-page: 3283
  year: 2020
  end-page: 3290
  ident: b2
  article-title: Smart contract vulnerability detection using graph neural network
  publication-title: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020
– volume: 62
  start-page: 19102:1
  year: 2019
  end-page: 19102:3
  ident: b1
  article-title: How security bugs are fixed and what can be improved: an empirical study with mozilla
  publication-title: Sci. China Inf. Sci.
– volume: 31
  start-page: 897
  year: 2005
  end-page: 910
  ident: b22
  article-title: Empirical validation of object-oriented metrics on open source software for fault prediction
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 477
  year: 2007
  end-page: 486
  ident: b35
  article-title: Automated vulnerability analysis: Leveraging control flow for evolutionary input crafting
  publication-title: 23rd Annual Computer Security Applications Conference (ACSAC 2007), December 10-14, 2007, Miami Beach, Florida, USA
– start-page: 265
  year: 2016
  end-page: 283
  ident: b38
  article-title: Tensorflow: A system for large-scale machine learning
  publication-title: 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA, November 2-4, 2016
– volume: 168
  year: 2020
  ident: b40
  article-title: The impact factors on the performance of machine learning-based vulnerability detection: A comparative study
  publication-title: J. Syst. Softw.
– volume: 37
  start-page: 772
  year: 2011
  end-page: 787
  ident: b6
  article-title: Evaluating complexity, code churn, and developer activity metrics as indicators of software vulnerabilities
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 4438
  year: 2018
  end-page: 4445
  ident: b41
  article-title: An end-to-end deep learning architecture for graph classification
  publication-title: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018
– year: 2018
  ident: b10
  article-title: Fuzzergym: A competitive framework for fuzzing and learning
– start-page: 1298
  year: 2017
  end-page: 1302
  ident: b29
  article-title: Vulnerability detection with deep learning
  publication-title: 2017 3rd IEEE International Conference on Computer and Communications (ICCC)
– start-page: 757
  year: 2018
  end-page: 762
  ident: b30
  article-title: Automated vulnerability detection in source code using deep representation learning
  publication-title: 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, FL, USA, December 17-20, 2018
– volume: 55
  start-page: 1397
  year: 2013
  end-page: 1418
  ident: b24
  article-title: Software fault prediction metrics: A systematic literature review
  publication-title: Inf. Softw. Technol.
– volume: 22
  start-page: 1305
  year: 2017
  end-page: 1347
  ident: b3
  article-title: Do bugs foreshadow vulnerabilities? An in-depth study of the chromium project
  publication-title: Empir. Softw. Eng.
– volume: 3
  year: 2020
  ident: b11
  article-title: VYPER: Vulnerability detection in binary code
  publication-title: Secur. Priv.
– volume: 24
  start-page: 2823
  year: 2019
  end-page: 2862
  ident: b26
  article-title: Revisiting supervised and unsupervised models for effort-aware just-in-time defect prediction
  publication-title: Empir. Softw. Eng.
– start-page: 376
  year: 2020
  end-page: 387
  ident: b17
  article-title: Patch based vulnerability matching for binary programs
  publication-title: ISSTA ’20: 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, Virtual Event, USA, July 18-22, 2020
– year: 2016
  ident: b33
  article-title: Gated graph sequence neural networks
  publication-title: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings
– volume: 163
  year: 2020
  ident: b8
  article-title: Analyzing bug fix for automatic bug cause classification
  publication-title: J. Syst. Softw.
– volume: 38
  start-page: 1276
  year: 2012
  end-page: 1304
  ident: b23
  article-title: A systematic literature review on fault prediction performance in software engineering
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 60
  year: 2019
  end-page: 71
  ident: b4
  article-title: Leopard: identifying vulnerable code for vulnerability assessment through program metrics
  publication-title: Proceedings of the 41st International Conference on Software Engineering, ICSE 2019, Montreal, QC, Canada, May 25-31, 2019
– volume: 44
  start-page: 25
  year: 2018
  end-page: 43
  ident: b12
  article-title: Eliminating path redundancy via postconditioned symbolic execution
  publication-title: IEEE Trans. Softw. Eng.
– volume: vol. 11999
  start-page: 199
  year: 2019
  end-page: 218
  ident: b13
  article-title: Vulhunter: An automated vulnerability detection system based on deep learning and bytecode
  publication-title: Information and Communications Security - 21st International Conference, ICICS 2019, Beijing, China, December 15-17, 2019, Revised Selected Papers
– year: 2018
  ident: b27
  article-title: Vuldeepecker: A deep learning-based system for vulnerability detection
  publication-title: 25th Annual Network and Distributed System Security Symposium, NDSS 2018, San Diego, California, USA, February 18-21, 2018
– start-page: 1
  year: 2020
  ident: b9
  article-title: Heuristic and neural network based prediction of project-specific api member access
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 371
  year: 2014
  end-page: 372
  ident: b15
  article-title: Droid-sec: deep learning in android malware detection
  publication-title: ACM SIGCOMM 2014 Conference, SIGCOMM’14, Chicago, IL, USA, August 17-22, 2014
– start-page: 45
  year: 2013
  end-page: 54
  ident: b36
  article-title: Structural detection of android malware using embedded call graphs
  publication-title: AISec’13, Proceedings of the 2013 ACM Workshop on Artificial Intelligence and Security, Co-Located with CCS 2013, Berlin, Germany, November 4, 2013
– year: 2018
  ident: b28
  article-title: Sysevr: A framework for using deep learning to detect software vulnerabilities
– year: 2017
  ident: b31
  article-title: Automatic feature learning for vulnerability prediction
– year: 2017
  ident: b37
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings
– start-page: 359
  year: 2012
  end-page: 368
  ident: b7
  article-title: Generalized vulnerability extrapolation using abstract syntax trees
  publication-title: 28th Annual Computer Security Applications Conference, ACSAC 2012, Orlando, FL, USA, 3-7 December 2012
– start-page: 97
  year: 2016
  end-page: 104
  ident: b43
  article-title: To fear or not to fear that is the question: Code characteristics of a vulnerable functionwith an existing exploit
  publication-title: Proceedings of the Sixth ACM on Conference on Data and Application Security and Privacy, CODASPY 2016, New Orleans, la, USA, March 9-11, 2016
– start-page: 10197
  year: 2019
  end-page: 10207
  ident: b32
  article-title: Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks
  publication-title: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada
– start-page: 452
  year: 2015
  end-page: 463
  ident: b20
  article-title: CLAMI: Defect prediction on unlabeled datasets (T)
  publication-title: 30th IEEE/ACM International Conference on Automated Software Engineering, ASE 2015, Lincoln, NE, USA, November 9-13, 2015
– start-page: 309
  year: 2016
  end-page: 320
  ident: b25
  article-title: Cross-project defect prediction using a connectivity-based unsupervised classifier
  publication-title: Proceedings of the 38th International Conference on Software Engineering, ICSE 2016, Austin, TX, USA, May 14-22, 2016
– year: 2015
  ident: b39
  article-title: Adam: A method for stochastic optimization
  publication-title: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings
– year: 2018
  ident: 10.1016/j.infsof.2021.106576_b10
– start-page: 595
  year: 2017
  ident: 10.1016/j.infsof.2021.106576_b5
  article-title: VUDDY: a scalable approach for vulnerable code clone discovery
– start-page: 4438
  year: 2018
  ident: 10.1016/j.infsof.2021.106576_b41
  article-title: An end-to-end deep learning architecture for graph classification
– volume: 31
  start-page: 897
  issue: 10
  year: 2005
  ident: 10.1016/j.infsof.2021.106576_b22
  article-title: Empirical validation of object-oriented metrics on open source software for fault prediction
  publication-title: IEEE Trans. Softw. Eng.
  doi: 10.1109/TSE.2005.112
– volume: 22
  start-page: 1305
  issue: 3
  year: 2017
  ident: 10.1016/j.infsof.2021.106576_b3
  article-title: Do bugs foreshadow vulnerabilities? An in-depth study of the chromium project
  publication-title: Empir. Softw. Eng.
  doi: 10.1007/s10664-016-9447-3
– start-page: 1
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b18
  article-title: Deep learning based code smell detection
  publication-title: IEEE Trans. Softw. Eng.
– volume: 38
  start-page: 1276
  issue: 6
  year: 2012
  ident: 10.1016/j.infsof.2021.106576_b23
  article-title: A systematic literature review on fault prediction performance in software engineering
  publication-title: IEEE Trans. Softw. Eng.
  doi: 10.1109/TSE.2011.103
– start-page: 477
  year: 2007
  ident: 10.1016/j.infsof.2021.106576_b35
  article-title: Automated vulnerability analysis: Leveraging control flow for evolutionary input crafting
– start-page: 45
  year: 2013
  ident: 10.1016/j.infsof.2021.106576_b36
  article-title: Structural detection of android malware using embedded call graphs
– start-page: 473
  year: 2018
  ident: 10.1016/j.infsof.2021.106576_b14
  article-title: Deeprefiner: Multi-layer android malware detection system applying deep neural networks
– volume: 2
  start-page: 147:1
  issue: OOPSLA
  year: 2018
  ident: 10.1016/j.infsof.2021.106576_b42
  article-title: Deepbugs: a learning approach to name-based bug detection
  publication-title: Proc. ACM Program. Lang.
  doi: 10.1145/3276517
– start-page: 1
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b9
  article-title: Heuristic and neural network based prediction of project-specific api member access
  publication-title: IEEE Trans. Softw. Eng.
– volume: 168
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b40
  article-title: The impact factors on the performance of machine learning-based vulnerability detection: A comparative study
  publication-title: J. Syst. Softw.
  doi: 10.1016/j.jss.2020.110659
– start-page: 371
  year: 2014
  ident: 10.1016/j.infsof.2021.106576_b15
  article-title: Droid-sec: deep learning in android malware detection
– year: 2015
  ident: 10.1016/j.infsof.2021.106576_b39
  article-title: Adam: A method for stochastic optimization
– year: 2016
  ident: 10.1016/j.infsof.2021.106576_b33
  article-title: Gated graph sequence neural networks
– volume: 163
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b8
  article-title: Analyzing bug fix for automatic bug cause classification
  publication-title: J. Syst. Softw.
  doi: 10.1016/j.jss.2020.110538
– start-page: 265
  year: 2016
  ident: 10.1016/j.infsof.2021.106576_b38
  article-title: Tensorflow: A system for large-scale machine learning
– volume: 62
  start-page: 19102:1
  issue: 1
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b1
  article-title: How security bugs are fixed and what can be improved: an empirical study with mozilla
  publication-title: Sci. China Inf. Sci.
  doi: 10.1007/s11432-017-9459-5
– year: 2018
  ident: 10.1016/j.infsof.2021.106576_b27
  article-title: Vuldeepecker: A deep learning-based system for vulnerability detection
– start-page: 368
  year: 1998
  ident: 10.1016/j.infsof.2021.106576_b34
  article-title: Clone detection using abstract syntax trees
– start-page: 3283
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b2
  article-title: Smart contract vulnerability detection using graph neural network
– start-page: 376
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b17
  article-title: Patch based vulnerability matching for binary programs
– volume: 55
  start-page: 1397
  issue: 8
  year: 2013
  ident: 10.1016/j.infsof.2021.106576_b24
  article-title: Software fault prediction metrics: A systematic literature review
  publication-title: Inf. Softw. Technol.
  doi: 10.1016/j.infsof.2013.02.009
– volume: 44
  start-page: 25
  issue: 1
  year: 2018
  ident: 10.1016/j.infsof.2021.106576_b12
  article-title: Eliminating path redundancy via postconditioned symbolic execution
  publication-title: IEEE Trans. Softw. Eng.
  doi: 10.1109/TSE.2017.2659751
– start-page: 359
  year: 2012
  ident: 10.1016/j.infsof.2021.106576_b7
  article-title: Generalized vulnerability extrapolation using abstract syntax trees
– volume: 37
  start-page: 772
  issue: 6
  year: 2011
  ident: 10.1016/j.infsof.2021.106576_b6
  article-title: Evaluating complexity, code churn, and developer activity metrics as indicators of software vulnerabilities
  publication-title: IEEE Trans. Softw. Eng.
  doi: 10.1109/TSE.2010.81
– year: 2017
  ident: 10.1016/j.infsof.2021.106576_b37
  article-title: Semi-supervised classification with graph convolutional networks
– start-page: 97
  year: 2016
  ident: 10.1016/j.infsof.2021.106576_b43
  article-title: To fear or not to fear that is the question: Code characteristics of a vulnerable functionwith an existing exploit
– start-page: 1
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b16
  article-title: Deep learning based program generation from requirements text: Are we there yet?
  publication-title: IEEE Trans. Softw. Eng.
– start-page: 60
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b4
  article-title: Leopard: identifying vulnerable code for vulnerability assessment through program metrics
– year: 2017
  ident: 10.1016/j.infsof.2021.106576_b31
– start-page: 10197
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b32
  article-title: Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks
– volume: 114
  start-page: 204
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b21
  article-title: Improving defect prediction with deep forest
  publication-title: Inf. Softw. Technol.
  doi: 10.1016/j.infsof.2019.07.003
– volume: 24
  start-page: 2823
  issue: 5
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b26
  article-title: Revisiting supervised and unsupervised models for effort-aware just-in-time defect prediction
  publication-title: Empir. Softw. Eng.
  doi: 10.1007/s10664-018-9661-2
– volume: 3
  issue: 2
  year: 2020
  ident: 10.1016/j.infsof.2021.106576_b11
  article-title: VYPER: Vulnerability detection in binary code
  publication-title: Secur. Priv.
– start-page: 452
  year: 2015
  ident: 10.1016/j.infsof.2021.106576_b20
  article-title: CLAMI: Defect prediction on unlabeled datasets (T)
– start-page: 462
  year: 2017
  ident: 10.1016/j.infsof.2021.106576_b19
  article-title: SPAIN: security patch analysis for binaries towards understanding the pain and pills
– year: 2018
  ident: 10.1016/j.infsof.2021.106576_b28
– volume: vol. 11999
  start-page: 199
  year: 2019
  ident: 10.1016/j.infsof.2021.106576_b13
  article-title: Vulhunter: An automated vulnerability detection system based on deep learning and bytecode
– start-page: 1298
  year: 2017
  ident: 10.1016/j.infsof.2021.106576_b29
  article-title: Vulnerability detection with deep learning
– start-page: 309
  year: 2016
  ident: 10.1016/j.infsof.2021.106576_b25
  article-title: Cross-project defect prediction using a connectivity-based unsupervised classifier
– start-page: 757
  year: 2018
  ident: 10.1016/j.infsof.2021.106576_b30
  article-title: Automated vulnerability detection in source code using deep representation learning
SSID ssj0017030
Score 2.665245
Snippet Previous studies have shown that existing deep learning-based approaches can significantly improve the performance of vulnerability detection. They represent...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 106576
SubjectTerms Bidirectional Graph Neural-Network
Code representation
Vulnerability detection
Title BGNN4VD: Constructing Bidirectional Graph Neural-Network for Vulnerability Detection
URI https://dx.doi.org/10.1016/j.infsof.2021.106576
Volume 136
WOSCitedRecordID wos000655363900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-6025
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017030
  issn: 0950-5849
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9QwDI9gQ4gXxKfY-FAeeJuCem2aprztxhggVCHtOB1PVZOm002nbuLKGP89dpx2dxziS-KlqqKmae1fbMexHcaea9mAUs6ciG2VClknUuSJiYRTJgN92MTGF9Kevs-KQs9m-YcQVrT0xwlkbasvL_Pz_8pqaANmY-rsX7B7eCk0wD0wHa7Adrj-EePHR0Uhp69wqY-ncVJ92PZkbzwn9UW-vyMsVL2HpTmqhSgoFtyHHE6_LLAQtY-Z_QbiqKMuq0ZsSGHq-kjmJYjyrxhB1m346Q8q74o9BrwFFek3oLyom80rTD4bmsdn5CRYzK-2i3yswaf-oeCdiEdDbFxwmW2kzQTfYyTA8iFZ6Ujy6iwRKqIs6EE0U3GUDTFPHodTXJvAL77AgaFRpdkPVbW9nj7G4XC0GPcyUq2us-04S3OQgdv7bw9n74ZdJ5R-VJuRPq9PtfTxgJtj_dyUWTFPJnfY7bCu4PuEh7vsmmvvsZt9WsN9NgmweMlXQcHXQME9KPg6KDjwmq-Bgg-geMA-vj6cHLwR4UQNYWFp2MEMzLXJK7ALrXVa10rJRicuMS5NE5sjieTI-IpAkczqylXSRiZumspheFGdPGRb7VnrHjEOM9zWKjVSjRxMcZsbJ2N4b-0UqP9a77CkJ05pQ7l5PPVkUfZxhaclkbREkpZE0h0mhl7nVG7lN89nPd3LYDIS2UqAyi977v5zz8fs1hXSn7AtYJl7ym7Yi26-_PwsYOo77uqSyA
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=BGNN4VD%3A+Constructing+Bidirectional+Graph+Neural-Network+for+Vulnerability+Detection&rft.jtitle=Information+and+software+technology&rft.au=Cao%2C+Sicong&rft.au=Sun%2C+Xiaobing&rft.au=Bo%2C+Lili&rft.au=Wei%2C+Ying&rft.date=2021-08-01&rft.pub=Elsevier+B.V&rft.issn=0950-5849&rft.eissn=1873-6025&rft.volume=136&rft_id=info:doi/10.1016%2Fj.infsof.2021.106576&rft.externalDocID=S0950584921000586
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-5849&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-5849&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-5849&client=summon