{"id":"https://openalex.org/W4415230479","doi":"https://doi.org/10.1609/aies.v8i1.36592","title":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","display_name":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415230479","doi":"https://doi.org/10.1609/aies.v8i1.36592"},"language":"en","primary_location":{"id":"doi:10.1609/aies.v8i1.36592","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36592","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36592/38730","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AIES/article/download/36592/38730","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120015971","display_name":"David Egea","orcid":null},"institutions":[{"id":"https://openalex.org/I96580804","display_name":"Universidad Pontificia Comillas","ror":"https://ror.org/017mdc710","country_code":"ES","type":"education","lineage":["https://openalex.org/I96580804"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Egea","raw_affiliation_strings":["Universidad Pontificia Comillas\nUniversity of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Pontificia Comillas\nUniversity of Maryland","institution_ids":["https://openalex.org/I96580804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111249532","display_name":"Barproda Halder","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barproda Halder","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035222388","display_name":"Sanghamitra Dutta","orcid":"https://orcid.org/0000-0002-6500-2627"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanghamitra Dutta","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.811,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93409199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"8","issue":"1","first_page":"812","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9821000099182129,"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"}},"topics":[{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9821000099182129,"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/T11424","display_name":"Security and Verification in Computing","score":0.9617999792098999,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9376999735832214,"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/spurious-relationship","display_name":"Spurious relationship","score":0.7465999722480774},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7353000044822693},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6909999847412109},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5541999936103821},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5138999819755554},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49160000681877136},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.42750000953674316}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7465999722480774},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7353000044822693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325000166893005},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6909999847412109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6344000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5541999936103821},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.42750000953674316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aies.v8i1.36592","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36592","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36592/38730","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36592","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AIES/article/view/36592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3065-8365","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aies.v8i1.36592","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36592","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36592/38730","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1790445677","display_name":"CAREER: Information-Theoretic Measures for Fairness and Explainability in High-Stakes Applications","funder_award_id":"2340006","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415230479.pdf","grobid_xml":"https://content.openalex.org/works/W4415230479.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"detection":[1],"of":[2,46,278],"vulnerabilities":[3],"in":[4,14,39,69,193],"source":[5],"code":[6,37,67,148,162],"is":[7,48],"an":[8],"essential":[9],"cybersecurity":[10,283],"challenge,":[11],"underpinning":[12],"trust":[13],"digital":[15],"systems":[16,284],"and":[17,35,55,96,153,181,185,207,239,261,269,280],"services.":[18],"Graph":[19],"Neural":[20],"Networks":[21],"(GNNs)":[22],"have":[23,121],"emerged":[24],"as":[25,29,189],"a":[26,40,90,109,135,245],"promising":[27],"approach":[28,274],"they":[30],"can":[31,59],"learn":[32,61],"the":[33,44,70,159,170,216,259],"structural":[34],"logical":[36],"relationships":[38],"data-driven":[41],"manner.":[42],"However,":[43],"performance":[45],"GNNs":[47,58],"severely":[49],"limited":[50],"by":[51,106,133,191,258],"training":[52,71,111,144],"data":[53],"imbalances":[54],"label":[56],"noise.":[57],"often":[60],"\u201cspurious\u201d":[62],"correlations":[63,105],"due":[64],"to":[65,74,81,157,198,205,213],"superficial":[66],"similarities":[68],"data,":[72],"leading":[73],"detectors":[75],"that":[76,120,175],"do":[77],"not":[78],"generalize":[79],"well":[80],"unseen":[82],"real-world":[83],"data.":[84],"In":[85],"this":[86],"work,":[87],"we":[88,100],"propose":[89],"new":[91,246],"unified":[92],"framework":[93,127,177],"for":[94,165,248,288],"robust":[95,184],"interpretable":[97],"vulnerability":[98,166,187,249],"detection\u2014that":[99],"call":[101],"VISION\u2014to":[102],"mitigate":[103],"spurious":[104,171,179],"systematically":[107],"augmenting":[108],"counterfactual":[110,270],"dataset.":[112],"Counterfactuals":[113],"are":[114],"samples":[115,254],"with":[116,150],"minimal":[117],"semantic":[118],"modifications":[119],"opposite":[122,151],"prediction":[123],"labels.":[124],"Our":[125],"complete":[126],"includes:":[128],"(i)":[129],"generating":[130],"effective":[131],"counterfactuals":[132],"prompting":[134],"Large":[136],"Language":[137],"Model":[138],"(LLM);":[139],"(ii)":[140],"targeted":[141],"GNN":[142],"model":[143],"on":[145,215],"synthetically":[146],"paired":[147],"examples":[149],"labels;":[152],"(iii)":[154],"graph-based":[155],"interpretability":[156],"identify":[158],"truly":[160],"crucial":[161],"statements":[163],"relevant":[164],"predictions":[167],"while":[168],"ignoring":[169],"ones.":[172],"We":[173,224,243],"find":[174],"our":[176,229,273],"reduces":[178],"learning":[180],"enables":[182],"more":[183],"generalizable":[186],"detection,":[188,250],"demonstrated":[190],"improvements":[192,227],"overall":[194],"accuracy":[195,202,209],"(from":[196,203,211],"51.8%":[197],"97.8%),":[199],"pairwise":[200],"contrast":[201],"4.5%":[204],"95.8%),":[206],"worst-group":[208],"increasing":[210],"0.7%":[212],"85.5%)":[214],"widely":[217],"popular":[218],"Common":[219],"Weakness":[220],"Enumeration":[221],"(CWE)-20":[222],"vulnerability.":[223],"also":[225],"demonstrate":[226],"using":[228],"proposed":[230],"metrics,":[231],"namely,":[232],"intra-class":[233],"attribution":[234,237],"variance,":[235],"inter-class":[236],"distance,":[238],"node":[240],"score":[241],"dependency.":[242],"provide":[244],"benchmark":[247],"CWE-20-CFA,":[251],"comprising":[252],"27,556":[253],"from":[255],"functions":[256],"affected":[257],"high-impact":[260],"frequently":[262],"occurring":[263],"CWE-20":[264],"vulnerability,":[265],"including":[266],"both":[267],"real":[268],"examples.":[271],"Furthermore,":[272],"enhances":[275],"societal":[276],"objectives":[277],"transparent":[279],"trustworthy":[281],"AI-based":[282],"through":[285],"interactive":[286],"visualization":[287],"human-in-the-loop":[289],"analysis.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-16T00:00:00"}