{"id":"https://openalex.org/W4399567378","doi":"https://doi.org/10.1145/3650105.3652299","title":"Fine Tuning Large Language Model for Secure Code Generation","display_name":"Fine Tuning Large Language Model for Secure Code Generation","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4399567378","doi":"https://doi.org/10.1145/3650105.3652299"},"language":"en","primary_location":{"id":"doi:10.1145/3650105.3652299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652299","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100367641","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0001-8828-632X"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Concordia University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8828-632X","affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011302872","display_name":"Aseem Sangalay","orcid":"https://orcid.org/0009-0005-9002-7841"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aseem Sangalay","raw_affiliation_strings":["Delhi Technological University, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0005-9002-7841","affiliations":[{"raw_affiliation_string":"Delhi Technological University, Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060578924","display_name":"\u7a0b\u8bda Cheng Cheng","orcid":"https://orcid.org/0000-0001-6962-6923"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cheng Cheng","raw_affiliation_strings":["Concordia University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6962-6923","affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716456","display_name":"Yuan Tian","orcid":"https://orcid.org/0000-0002-2208-3893"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuan Tian","raw_affiliation_strings":["Queen's University, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2208-3893","affiliations":[{"raw_affiliation_string":"Queen's University, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101712379","display_name":"Jinqiu Yang","orcid":"https://orcid.org/0000-0003-4282-406X"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jinqiu Yang","raw_affiliation_strings":["Concordia University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4282-406X","affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100367641"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":16.412,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.99058779,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9976000189781189,"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":0.9976000189781189,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9860000014305115,"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/computer-science","display_name":"Computer science","score":0.8595424294471741},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.7654077410697937},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6909703612327576},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6550518274307251},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5661759376525879},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44158387184143066},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3979525864124298},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18916302919387817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595424294471741},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7654077410697937},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6909703612327576},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6550518274307251},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5661759376525879},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44158387184143066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3979525864124298},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18916302919387817},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650105.3652299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650105.3652299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650105.3652299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650105.3652299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399567378.pdf","grobid_xml":"https://content.openalex.org/works/W4399567378.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2770568736","https://openalex.org/W3091588759","https://openalex.org/W3098605233","https://openalex.org/W3162364548","https://openalex.org/W3163206498","https://openalex.org/W3170092793","https://openalex.org/W3183469243","https://openalex.org/W3193639695","https://openalex.org/W3195703954","https://openalex.org/W4221141536","https://openalex.org/W4224060952","https://openalex.org/W4226205863","https://openalex.org/W4226326075","https://openalex.org/W4281567711","https://openalex.org/W4281763794","https://openalex.org/W4281836191","https://openalex.org/W4282813445","https://openalex.org/W4285225959","https://openalex.org/W4288057765","https://openalex.org/W4320560161","https://openalex.org/W4385187279","https://openalex.org/W4388867283"],"related_works":["https://openalex.org/W2095999892","https://openalex.org/W2018764758","https://openalex.org/W2383689843","https://openalex.org/W3081644756","https://openalex.org/W3122369893","https://openalex.org/W2407476586","https://openalex.org/W2048831961","https://openalex.org/W2799261831","https://openalex.org/W1606349578","https://openalex.org/W2750654225"],"abstract_inverted_index":{"AI":[0],"pair":[1],"programmers,":[2],"such":[3,16],"as":[4,54],"GitHub's":[5],"Copilot,":[6],"have":[7],"shown":[8],"great":[9],"success":[10],"in":[11],"automatic":[12],"code":[13,20,90],"generation.":[14],"However,":[15],"large":[17,41,114],"language":[18,42,115],"model-based":[19],"generation":[21,91],"techniques":[22],"face":[23],"the":[24,37,69,80,112],"risk":[25],"of":[26,39,88],"introducing":[27],"security":[28],"vulnerabilities":[29],"to":[30],"codebases.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"explore":[36],"direction":[38],"fine-tuning":[40,56],"models":[43],"for":[44,65,92,102,108],"generating":[45],"more":[46],"secure":[47],"code.":[48],"We":[49,58],"use":[50],"real-world":[51],"vulnerability":[52],"fixes":[53],"our":[55],"dataset.":[57],"craft":[59],"a":[60,99,105],"code-generation":[61],"scenario":[62],"dataset":[63],"(C/C++)":[64],"evaluating":[66],"and":[67,71,85,94,104],"comparing":[68],"pre-trained":[70,113],"fine-tuned":[72,81],"models.":[73],"Our":[74],"experiments":[75],"on":[76],"GPT-J":[77,82],"show":[78],"that":[79],"achieved":[83],"70.4%":[84],"64.5%":[86],"ratios":[87],"non-vulnerable":[89],"C":[93,103],"C++,":[95],"respectively,":[96],"which":[97],"has":[98],"10%":[100],"increase":[101,107],"slight":[106],"C++":[109],"compared":[110],"with":[111],"model.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}