{"id":"https://openalex.org/W4389215044","doi":"https://doi.org/10.1145/3617555.3617874","title":"The FormAI Dataset: Generative AI in Software Security through the Lens of Formal Verification","display_name":"The FormAI Dataset: Generative AI in Software Security through the Lens of Formal Verification","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4389215044","doi":"https://doi.org/10.1145/3617555.3617874"},"language":"en","primary_location":{"id":"doi:10.1145/3617555.3617874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617555.3617874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617555.3617874","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 19th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3617555.3617874","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073042391","display_name":"Norbert Tihanyi","orcid":"https://orcid.org/0000-0002-9002-5935"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Norbert Tihanyi","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052473439","display_name":"Tam\u00e1s Bisztray","orcid":"https://orcid.org/0000-0003-2626-3434"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tamas Bisztray","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012126","display_name":"Ridhi Jain","orcid":"https://orcid.org/0000-0002-6102-7114"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ridhi Jain","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026903935","display_name":"Mohamed Amine Ferrag","orcid":"https://orcid.org/0000-0002-0632-3172"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohamed Amine Ferrag","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057689302","display_name":"Lucas C. Cordeiro","orcid":"https://orcid.org/0000-0002-6235-4272"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucas C. Cordeiro","raw_affiliation_strings":["University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051922069","display_name":"Vasileios Mavroeidis","orcid":"https://orcid.org/0000-0002-8188-3575"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Vasileios Mavroeidis","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8409304618835449},{"id":"https://openalex.org/keywords/satisfiability-modulo-theories","display_name":"Satisfiability modulo theories","score":0.6556547284126282},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6000251770019531},{"id":"https://openalex.org/keywords/debugger","display_name":"Debugger","score":0.4813133478164673},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4410731792449951},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3871188461780548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38166260719299316},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3321724534034729},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.14050036668777466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409304618835449},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.6556547284126282},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6000251770019531},{"id":"https://openalex.org/C2778485113","wikidata":"https://www.wikidata.org/wiki/Q193231","display_name":"Debugger","level":3,"score":0.4813133478164673},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4410731792449951},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3871188461780548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38166260719299316},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3321724534034729},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.14050036668777466}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617555.3617874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617555.3617874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617555.3617874","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 19th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3617555.3617874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617555.3617874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617555.3617874","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 19th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1147893575","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2236787230","display_name":null,"funder_award_id":"957286","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G257784197","display_name":null,"funder_award_id":"EU H2020 ELEGANT 957286","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3060584250","display_name":"SCorCH: Secure Code for Capability Hardware","funder_award_id":"EP/V000497/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5045220161","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6661291015","display_name":"EnnCore: End-to-End Conceptual Guarding of Neural Architectures","funder_award_id":"EP/T026995/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7331901853","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G849311619","display_name":null,"funder_award_id":"EP/T026995/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320323260","display_name":"Universitetet i Oslo","ror":"https://ror.org/01xtthb56"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320335813","display_name":"Innovation and Networks Executive Agency","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389215044.pdf","grobid_xml":"https://content.openalex.org/works/W4389215044.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W327452528","https://openalex.org/W1705210632","https://openalex.org/W2006849174","https://openalex.org/W2031525781","https://openalex.org/W2067705817","https://openalex.org/W2511803001","https://openalex.org/W2802300457","https://openalex.org/W2888321432","https://openalex.org/W2899171197","https://openalex.org/W2949558051","https://openalex.org/W2962960733","https://openalex.org/W2963762601","https://openalex.org/W2972135640","https://openalex.org/W3091588759","https://openalex.org/W3119097978","https://openalex.org/W3166095789","https://openalex.org/W4221143046","https://openalex.org/W4287022754","https://openalex.org/W4321013654","https://openalex.org/W4321354332","https://openalex.org/W4321649710","https://openalex.org/W4323927271","https://openalex.org/W4324370640","https://openalex.org/W4366449580","https://openalex.org/W4367860052","https://openalex.org/W4377866432","https://openalex.org/W4378473878","https://openalex.org/W4379539348","https://openalex.org/W4385187279","https://openalex.org/W4387298393","https://openalex.org/W4388858772","https://openalex.org/W4391307510","https://openalex.org/W6907179428"],"related_works":["https://openalex.org/W2096138810","https://openalex.org/W170948064","https://openalex.org/W4239256660","https://openalex.org/W2153064384","https://openalex.org/W171936820","https://openalex.org/W2185368734","https://openalex.org/W2124217695","https://openalex.org/W3018143143","https://openalex.org/W1549970137","https://openalex.org/W4384377078"],"abstract_inverted_index":{"This":[0,93,129],"paper":[1],"presents":[2],"the":[3,77,81,85,103,145,155,166,171,180,187,206],"FormAI":[4],"dataset,":[5],"a":[6,22,98,136,141,176],"large":[7],"collection":[8],"of":[9,49,147,205],"112,000":[10,172],"AI-generated":[11],"compilable":[12],"and":[13,43,89,118,134,193,220],"independent":[14],"C":[15],"programs":[16,31,45,52,207],"with":[17,46,66,76,158],"vulnerability":[18],"classification.":[19],"We":[20,152,164],"introduce":[21],"dynamic":[23],"zero-shot":[24],"prompting":[25],"technique":[26],"constructed":[27],"to":[28,122,202,217],"spawn":[29],"diverse":[30],"utilizing":[32],"Large":[33],"Language":[34],"Models":[35],"(LLMs).":[36],"The":[37],"dataset":[38,188],"is":[39,74,94],"generated":[40,208],"by":[41,96,175,209],"GPT-3.5-turbo":[42],"comprises":[44],"varying":[47],"levels":[48],"complexity.":[50],"Some":[51],"handle":[53],"complicated":[54],"tasks":[55,68],"like":[56,69],"network":[57],"management,":[58],"table":[59],"games,":[60],"or":[61],"encryption,":[62],"while":[63],"others":[64],"deal":[65],"simpler":[67],"string":[70],"manipulation.":[71],"Every":[72],"program":[73],"labeled":[75],"vulnerabilities":[78,133,157,181],"found":[79],"within":[80],"source":[82,167],"code,":[83],"indicating":[84],"type,":[86],"line":[87],"number,":[88],"vulnerable":[90],"function":[91],"name.":[92],"accomplished":[95],"employing":[97],"formal":[99,137],"verification":[100],"method":[101],"using":[102],"Efficient":[104],"SMT-based":[105],"Bounded":[106],"Model":[107],"Checker":[108],"(ESBMC),":[109],"which":[110],"uses":[111],"model":[112,138],"checking,":[113],"abstract":[114],"interpretation,":[115],"constraint":[116],"programming,":[117],"satisfiability":[119],"modulo":[120],"theories":[121],"reason":[123],"over":[124],"safety/security":[125],"properties":[126],"in":[127,183],"programs.":[128],"approach":[130],"definitively":[131],"detects":[132],"offers":[135],"known":[139],"as":[140],"counterexample,":[142],"thus":[143],"eliminating":[144],"possibility":[146],"generating":[148],"false":[149],"positive":[150],"reports.":[151],"have":[153],"associated":[154],"identified":[156],"Common":[159],"Weakness":[160],"Enumeration":[161],"(CWE)":[162],"numbers.":[163],"make":[165],"code":[168],"available":[169],"for":[170,190],"programs,":[173],"accompanied":[174],"separate":[177],"file":[178],"containing":[179],"detected":[182],"each":[184],"program,":[185],"making":[186],"ideal":[189],"training":[191],"LLMs":[192],"machine":[194],"learning":[195],"algorithms.":[196],"Our":[197],"study":[198],"unveiled":[199],"that":[200],"according":[201],"ESBMC,":[203],"51.24%":[204],"GPT-3.5":[210],"contained":[211],"vulnerabilities,":[212],"thereby":[213],"presenting":[214],"considerable":[215],"risks":[216],"software":[218],"safety":[219],"security.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":18}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
