{"id":"https://openalex.org/W4403413408","doi":"https://doi.org/10.1145/3674805.3686674","title":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","display_name":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","publication_year":2024,"publication_date":"2024-10-15","ids":{"openalex":"https://openalex.org/W4403413408","doi":"https://doi.org/10.1145/3674805.3686674"},"language":"en","primary_location":{"id":"doi:10.1145/3674805.3686674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686674","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3674805.3686674","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017801401","display_name":"Triet Huynh Minh Le","orcid":"https://orcid.org/0000-0003-1935-037X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Triet Huynh Minh Le","raw_affiliation_strings":["CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1935-037X","affiliations":[{"raw_affiliation_string":"CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103075476","display_name":"Muhammad Ali Babar","orcid":"https://orcid.org/0000-0001-9696-3626"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Babar","raw_affiliation_strings":["CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9696-3626","affiliations":[{"raw_affiliation_string":"CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":3.1346,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93188503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996999979019165,"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":0.996999979019165,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.996399998664856,"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":0.7016114592552185},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6807190179824829},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5146318674087524},{"id":"https://openalex.org/keywords/vulnerability-assessment","display_name":"Vulnerability assessment","score":0.5088043808937073},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3712792992591858},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09947514533996582},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0664122998714447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016114592552185},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6807190179824829},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5146318674087524},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.5088043808937073},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3712792992591858},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09947514533996582},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0664122998714447},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674805.3686674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686674","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3674805.3686674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686674","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1818897895","https://openalex.org/W1832693441","https://openalex.org/W1971733255","https://openalex.org/W2059185913","https://openalex.org/W2081580037","https://openalex.org/W2094947835","https://openalex.org/W2108629901","https://openalex.org/W2143017621","https://openalex.org/W2148143831","https://openalex.org/W2155617465","https://openalex.org/W2241929320","https://openalex.org/W2289443514","https://openalex.org/W2565077509","https://openalex.org/W2568720339","https://openalex.org/W2570094557","https://openalex.org/W2599482629","https://openalex.org/W2748690817","https://openalex.org/W2752929869","https://openalex.org/W2767521898","https://openalex.org/W2771090858","https://openalex.org/W2805001156","https://openalex.org/W2890264517","https://openalex.org/W2902415484","https://openalex.org/W2906845177","https://openalex.org/W2914851262","https://openalex.org/W2918408501","https://openalex.org/W2938063707","https://openalex.org/W2963216553","https://openalex.org/W2963980822","https://openalex.org/W2967556797","https://openalex.org/W2971644666","https://openalex.org/W2982413960","https://openalex.org/W3006127095","https://openalex.org/W3043970365","https://openalex.org/W3080878745","https://openalex.org/W3083954092","https://openalex.org/W3091730360","https://openalex.org/W3128039057","https://openalex.org/W3142656464","https://openalex.org/W3156556445","https://openalex.org/W3176465319","https://openalex.org/W3180181113","https://openalex.org/W3184339106","https://openalex.org/W3195612455","https://openalex.org/W4210443011","https://openalex.org/W4249033934","https://openalex.org/W4285051903","https://openalex.org/W4287168322","https://openalex.org/W4287751558","https://openalex.org/W4312439220","https://openalex.org/W4313199266","https://openalex.org/W4384159091","https://openalex.org/W4384302803","https://openalex.org/W4386566574","https://openalex.org/W4393406994","https://openalex.org/W6778883912","https://openalex.org/W6795470022"],"related_works":["https://openalex.org/W1883246888","https://openalex.org/W2370114625","https://openalex.org/W1756374135","https://openalex.org/W2062873522","https://openalex.org/W2947584067","https://openalex.org/W3118510577","https://openalex.org/W2280562859","https://openalex.org/W230721595","https://openalex.org/W3157230915","https://openalex.org/W1496728123"],"abstract_inverted_index":{"Background:":[0],"Software":[1],"Vulnerability":[2,34],"(SV)":[3],"assessment":[4,26,46,88,118],"is":[5],"increasingly":[6],"adopted":[7],"to":[8,23,75,102,156],"address":[9],"the":[10,29,32,49,53,67,77,84,90,104,108,114,124,144,151,179,182,188,191],"ever-increasing":[11],"volume":[12],"and":[13,43,64,82,121,175,190],"complexity":[14],"of":[15,31,52,79,92,107,116,147],"SVs.":[16],"Data-driven":[17],"approaches":[18],"have":[19],"been":[20,61],"widely":[21],"used":[22],"automate":[24],"SV":[25,45,87,117,201],"tasks,":[27,153],"particularly":[28],"prediction":[30],"Common":[33],"Scoring":[35],"System":[36],"(CVSS)":[37],"metrics":[38],"such":[39,57],"as":[40],"exploitability,":[41],"impact,":[42],"severity.":[44],"suffers":[47],"from":[48],"imbalanced":[50],"distributions":[51,106],"CVSS":[54,109,152],"classes,":[55],"but":[56],"data":[58,80,93,99,139,197],"imbalance":[59,81,140,198],"has":[60],"hardly":[62],"understood":[63],"addressed":[65],"in":[66,158],"literature.":[68],"Aims:":[69],"We":[70,96,111,162],"conduct":[71],"a":[72],"large-scale":[73],"study":[74,186],"quantify":[76],"impacts":[78],"mitigate":[83],"issue":[85],"for":[86,149,199],"through":[89],"use":[91],"augmentation.":[94],"Method:":[95],"leverage":[97],"nine":[98],"augmentation":[100,168],"techniques":[101],"balance":[103],"class":[105],"metrics.":[110],"then":[112],"compare":[113],"performance":[115,146],"models":[119,148],"with":[120],"without":[122],"leveraging":[123],"augmented":[125],"data.":[126],"Results:":[127],"Through":[128],"extensive":[129],"experiments":[130],"on":[131],"180k+":[132],"real-world":[133],"SVs,":[134],"we":[135],"show":[136],"that":[137,165],"mitigating":[138],"can":[141,177],"significantly":[142],"improve":[143],"predictive":[145],"all":[150],"by":[154],"up":[155],"31.8%":[157],"Matthews":[159],"Correlation":[160],"Coefficient.":[161],"also":[163],"discover":[164],"simple":[166],"text":[167,172],"like":[169],"combining":[170],"random":[171],"insertion,":[173],"deletion,":[174],"replacement":[176],"outperform":[178],"baseline":[180],"across":[181],"board.":[183],"Conclusions:":[184],"Our":[185],"provides":[187],"motivation":[189],"first":[192],"promising":[193],"step":[194],"toward":[195],"tackling":[196],"effective":[200],"assessment.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}