{"id":"https://openalex.org/W4416251284","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229257","title":"SRVul: A High-Quality Self-Restrained Vulnerable Code Dataset for Vulnerability Detection","display_name":"SRVul: A High-Quality Self-Restrained Vulnerable Code Dataset for Vulnerability Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251284","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229257"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101964055","display_name":"Hongjun Huang","orcid":"https://orcid.org/0000-0001-5323-5389"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjun Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066205926","display_name":"Futai Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Futai Zou","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002240947","display_name":"Jiaping Gui","orcid":"https://orcid.org/0009-0001-4272-9604"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaping Gui","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042050954","display_name":"Tianming Zheng","orcid":"https://orcid.org/0000-0001-9813-6739"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianming Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101826653","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0003-4151-4596"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.6614999771118164,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.6614999771118164,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.0908999964594841,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.08290000259876251,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.7148000001907349},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5946999788284302},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5848000049591064},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.46549999713897705},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.462799996137619},{"id":"https://openalex.org/keywords/vulnerability-assessment","display_name":"Vulnerability assessment","score":0.45750001072883606},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.43140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694000005722046},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.7148000001907349},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.46549999713897705},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.45750001072883606},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.43140000104904175},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C176035894","wikidata":"https://www.wikidata.org/wiki/Q7554350","display_name":"Software quality control","level":5,"score":0.32280001044273376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C91071405","wikidata":"https://www.wikidata.org/wiki/Q1413145","display_name":"Program slicing","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C62913178","wikidata":"https://www.wikidata.org/wiki/Q7554361","display_name":"Software security assurance","level":4,"score":0.2651999890804291},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C172776598","wikidata":"https://www.wikidata.org/wiki/Q7943570","display_name":"Vulnerability management","level":4,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1997646511","https://openalex.org/W2048899404","https://openalex.org/W2093897789","https://openalex.org/W2105767494","https://openalex.org/W2165597437","https://openalex.org/W2762227829","https://openalex.org/W2765793020","https://openalex.org/W2781491433","https://openalex.org/W2885030880","https://openalex.org/W2899407111","https://openalex.org/W2962960733","https://openalex.org/W2965861627","https://openalex.org/W2967556797","https://openalex.org/W2979792666","https://openalex.org/W2998879504","https://openalex.org/W3033777149","https://openalex.org/W3084812981","https://openalex.org/W3091588759","https://openalex.org/W3111602563","https://openalex.org/W3161071537","https://openalex.org/W3163206498","https://openalex.org/W3166095789","https://openalex.org/W3177116043","https://openalex.org/W3183469243","https://openalex.org/W3195686297","https://openalex.org/W3195703954","https://openalex.org/W3199693282","https://openalex.org/W4210493608","https://openalex.org/W4221166942","https://openalex.org/W4225673889","https://openalex.org/W4226043105","https://openalex.org/W4233410239","https://openalex.org/W4292158679","https://openalex.org/W4301168982","https://openalex.org/W4312436517","https://openalex.org/W4312640079","https://openalex.org/W4312969325","https://openalex.org/W4383215759","https://openalex.org/W4384345694","https://openalex.org/W4384345698","https://openalex.org/W4387298393","https://openalex.org/W4394769548"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"software":[1,16,24,83,195],"vulnerability":[2,25,84,132,143,196,233,283],"detection":[3,26,234,284],"using":[4,229],"learning-based":[5],"approaches":[6],"has":[7,98],"been":[8,60,99],"a":[9,115,135,157,174,253],"focal":[10],"point":[11],"in":[12,44,173],"the":[13,19,32,35,78,90,106,124,178,183,188,216,220,223,226,244,261,279],"field":[14],"of":[15,23,34,77,82,92,169,177,190,218,222,228,247,282],"engineering.":[17],"However,":[18],"training":[20,36,71,232,281],"and":[21,52,72,118,127,153,198,225,250,255,258],"benchmarking":[22],"models":[27],"are":[28],"significantly":[29],"influenced":[30],"by":[31],"quality":[33,47,66,86,104,189],"data.":[37],"Existing":[38],"solutions":[39],"have":[40,59],"made":[41],"limited":[42,51],"efforts":[43],"addressing":[45],"data":[46,54,65,85,103,116,200],"issues":[48],"due":[49],"to":[50,62,89,101,140,166],"challenging":[53],"collection.":[55],"Publicly":[56],"available":[57,131],"datasets":[58],"found":[61],"suffer":[63],"from":[64,129],"problems,":[67],"hindering":[68],"effective":[69,256,280],"model":[70,264],"performance":[73,269],"evaluation.":[74],"Although":[75],"awareness":[76],"potential":[79],"negative":[80],"impact":[81],"is":[87,138,164,182,276],"increasing,":[88],"best":[91,245],"our":[93,212],"knowledge,":[94],"no":[95],"systematic":[96],"solution":[97],"proposed":[100],"improve":[102],"during":[105],"automated":[107],"labeling":[108],"process.":[109],"In":[110,211],"this":[111],"paper,":[112],"we":[113,214],"propose":[114],"collection":[117],"cleansing":[119],"framework":[120,185,257],"that":[121,186,274],"first":[122,184],"collects":[123],"latest":[125],"vulnerabilities":[126],"patches":[128],"publicly":[130],"databases.":[133],"Then,":[134],"rule-based":[136],"filter":[137,159,167],"applied":[139],"classify":[141],"function-level":[142,191],"fixing":[144],"modifications":[145],"into":[146],"three":[147],"categories:":[148],"high":[149],"quality,":[150,152,171,251],"unknown":[151,170],"low":[154],"quality.":[155],"Subsequently,":[156],"semantic":[158],"trained":[160],"on":[161,205,240,270],"high-quality":[162],"samples":[163,168,193],"used":[165],"resulting":[172],"cleansed":[175],"version":[176],"raw":[179],"dataset.":[180],"This":[181],"distinguishes":[187],"modification":[192],"for":[194,231,278],"fixes":[197],"performs":[199],"cleansing,":[201],"without":[202],"solely":[203],"relying":[204],"traditional":[206],"heuristic":[207],"label":[208],"assignment":[209],"strategies.":[210],"experiments,":[213],"evaluate":[215],"properties":[217],"SRVul,":[219],"effectiveness":[221],"framework,":[224],"feasibility":[227],"it":[230],"models.":[235,285],"SRVul":[236,266,275],"outperforms":[237],"existing":[238],"works":[239],"multiple":[241],"metrics,":[242],"demonstrating":[243],"combination":[246],"dataset":[248],"scale":[249],"with":[252,265],"well-designed":[254],"components.":[259],"Training":[260],"advanced":[262],"LineVul":[263],"yields":[267],"improved":[268],"benchmark":[271],"datasets,":[272],"indicating":[273],"well-suited":[277]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}