{"id":"https://openalex.org/W4409882770","doi":"https://doi.org/10.1109/access.2025.3564818","title":"Leveraging Cross-Project Similarity for Data Augmentation and Security Bug Report Prediction","display_name":"Leveraging Cross-Project Similarity for Data Augmentation and Security Bug Report Prediction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409882770","doi":"https://doi.org/10.1109/access.2025.3564818"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3564818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564818","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3564818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115830585","display_name":"Jinfeng Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I119060216","display_name":"Hankyong National University","ror":"https://ror.org/0031nsg68","country_code":"KR","type":"education","lineage":["https://openalex.org/I119060216"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinfeng Ji","raw_affiliation_strings":["Department of Computer Applied Mathematics, Hankyong National University, Anseong, South Korea","Department of Computer Science and Engineering, Hankyong National University, Korea"],"raw_orcid":"https://orcid.org/0009-0005-4627-9304","affiliations":[{"raw_affiliation_string":"Department of Computer Applied Mathematics, Hankyong National University, Anseong, South Korea","institution_ids":["https://openalex.org/I119060216"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Hankyong National University, Korea","institution_ids":["https://openalex.org/I119060216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033095132","display_name":"Geunseok Yang","orcid":"https://orcid.org/0000-0001-5677-5129"},"institutions":[{"id":"https://openalex.org/I119060216","display_name":"Hankyong National University","ror":"https://ror.org/0031nsg68","country_code":"KR","type":"education","lineage":["https://openalex.org/I119060216"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geunseok Yang","raw_affiliation_strings":["Department of Computer Applied Mathematics, Computer System Institute, Hankyong National University, Anseong, South Korea","Department of Computer Applied Mathematics, Hankyong National University (Computer System Institute), Korea"],"raw_orcid":"https://orcid.org/0000-0001-5677-5129","affiliations":[{"raw_affiliation_string":"Department of Computer Applied Mathematics, Computer System Institute, Hankyong National University, Anseong, South Korea","institution_ids":["https://openalex.org/I119060216"]},{"raw_affiliation_string":"Department of Computer Applied Mathematics, Hankyong National University (Computer System Institute), Korea","institution_ids":["https://openalex.org/I119060216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.3589,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87636178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"80416","last_page":"80428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9947999715805054,"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":0.9947999715805054,"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/T11719","display_name":"Data Quality and Management","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.9706000089645386,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641137838363647},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5798913836479187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4385729134082794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33417683839797974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2880513370037079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641137838363647},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5798913836479187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4385729134082794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33417683839797974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2880513370037079},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3564818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564818","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8852e616df484a34a95c7e7f9c91f341","is_oa":true,"landing_page_url":"https://doaj.org/article/8852e616df484a34a95c7e7f9c91f341","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 80416-80428 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3564818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564818","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W9328536","https://openalex.org/W1024906986","https://openalex.org/W1584308190","https://openalex.org/W1881549354","https://openalex.org/W1976526581","https://openalex.org/W1981109290","https://openalex.org/W2004025009","https://openalex.org/W2023511777","https://openalex.org/W2402268235","https://openalex.org/W2742191951","https://openalex.org/W2781021471","https://openalex.org/W2808393507","https://openalex.org/W2886714101","https://openalex.org/W2922023100","https://openalex.org/W2940758038","https://openalex.org/W2944955910","https://openalex.org/W2945475639","https://openalex.org/W2952767732","https://openalex.org/W2970641574","https://openalex.org/W2979860911","https://openalex.org/W3015200424","https://openalex.org/W3037686829","https://openalex.org/W3085039126","https://openalex.org/W3085062472","https://openalex.org/W3093815602","https://openalex.org/W3111871824","https://openalex.org/W3134770171","https://openalex.org/W3145506869","https://openalex.org/W3152377126","https://openalex.org/W3216799472","https://openalex.org/W4206344704","https://openalex.org/W4210448408","https://openalex.org/W4213370869","https://openalex.org/W4220744467","https://openalex.org/W4288048341","https://openalex.org/W4300164480","https://openalex.org/W4317497242"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Introduction:":[0],"Bug":[1],"reports":[2,26],"are":[3,27],"typically":[4],"classified":[5],"into":[6],"two":[7],"categories:":[8],"security":[9,40,53,72,92,236,251],"and":[10,38,85,90,100,129,156,161,177,202,214,226,267],"non-security.":[11],"However,":[12],"due":[13],"to":[14,32,51,114,131,151],"the":[15,45,105,140,164,198,217,248],"varying":[16],"levels":[17],"of":[18,142,167,219,250],"expertise":[19],"among":[20],"bug":[21,25,54,73,93,237,252],"reporters,":[22],"some":[23],"security-related":[24,262],"misclassified":[28],"as":[29],"non-security,":[30],"leading":[31],"an":[33,48],"increased":[34],"workload":[35],"for":[36,47,71,235],"developers":[37,258],"potential":[39],"risks.":[41],"This":[42,254],"issue":[43,201],"highlights":[44,216],"need":[46],"effective":[49],"method":[50],"identify":[52],"reports.":[55,103,253],"Methods:":[56],"To":[57],"address":[58],"this":[59],"challenge,":[60],"we":[61,108],"propose":[62],"a":[63,182],"predictive":[64],"approach":[65,255],"that":[66,192],"based":[67],"deep":[68,121],"learning":[69,122],"models":[70,176,213],"report":[74],"classification.":[75],"We":[76,118],"extract":[77],"data":[78,112,194,244],"from":[79,149],"four":[80],"open-source":[81],"projects\u2014Ambari,":[82],"Camel,":[83],"Derby,":[84],"Wicket\u2014containing":[86],"56,":[87],"74,":[88],"179,":[89],"47":[91],"reports,":[94],"respectively,":[95],"alongside":[96],"944,":[97],"926,":[98],"821,":[99],"953":[101],"non-security":[102],"Given":[104],"imbalanced":[106],"dataset,":[107],"employ":[109],"cross-project":[110,193,242],"similarity-based":[111,243],"augmentation":[113,195,245],"enhance":[115],"model":[116,204,220],"training.":[117],"evaluate":[119],"multiple":[120],"models,":[123,231],"including":[124],"CNN,":[125],"LSTM,":[126],"GRU,":[127],"Transformer,":[128],"BERT,":[130],"improve":[132],"classification":[133,186,223,238],"accuracy.":[134,187],"Results:":[135],"The":[136,169,189,206],"experimental":[137],"results":[138,190],"demonstrate":[139],"effectiveness":[141],"our":[143],"approach,":[144],"achieving":[145],"F1":[146,172,209],"scores":[147,210],"ranging":[148],"0.60":[150],"0.98.":[152,168],"LSTM":[153,225],"on":[154,158,222],"Ambari":[155,160],"GRU":[157,227],"both":[159],"Camel":[162],"achieved":[163],"highest":[165],"performance":[166],"overall":[170,269],"average":[171],"score":[173],"across":[174,211],"all":[175],"datasets":[178,215],"is":[179],"0.77,":[180],"indicating":[181],"notable":[183],"improvement":[184],"in":[185,208],"Discussion:":[188],"suggest":[191],"effectively":[196,260],"mitigates":[197],"class":[199],"imbalance":[200],"enhances":[203],"performance.":[205],"variation":[207],"different":[212],"impact":[218],"selection":[221],"effectiveness.":[224],"consistently":[228],"outperform":[229],"other":[230],"demonstrating":[232],"their":[233],"suitability":[234],"tasks.":[239],"Conclusion:":[240],"Incorporating":[241],"significantly":[246],"improves":[247],"identification":[249],"can":[256],"help":[257],"more":[259],"detect":[261],"issues,":[263],"reducing":[264],"misclassification":[265],"risks":[266],"enhancing":[268],"software":[270],"security.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}