{"id":"https://openalex.org/W4415318208","doi":"https://doi.org/10.48550/arxiv.2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","display_name":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4415318208","doi":"https://doi.org/10.48550/arxiv.2510.07189"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.07189","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07189","pdf_url":"https://arxiv.org/pdf/2510.07189","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.07189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100367641","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0001-8828-632X","observed_orcids":["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":false,"raw_author_name":"Li, Junjie","raw_affiliation_strings":["Concordia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000311674","display_name":"Fazle Rabbi","orcid":"https://orcid.org/0000-0001-5626-0598","observed_orcids":["https://orcid.org/0000-0001-5626-0598","https://orcid.org/0009-0007-8992-9682"]},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"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":"Rabbi, Fazle","raw_affiliation_strings":["Concordia University","York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049962443","display_name":"Bo Wen Yang","orcid":"https://orcid.org/0000-0001-6867-1976","observed_orcids":["https://orcid.org/0000-0001-6867-1976"]},"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":"Yang, Bo","raw_affiliation_strings":["Concordia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326214","display_name":"Song Wang","orcid":"https://orcid.org/0000-0003-0617-2877","observed_orcids":["https://orcid.org/0000-0003-0617-2877","https://orcid.org/0000-0003-0531-5717"]},"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":"Wang, Song","raw_affiliation_strings":["Concordia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101712379","display_name":"Jinqiu Yang","orcid":"https://orcid.org/0000-0003-4282-406X","observed_orcids":["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":"Yang, Jinqiu","raw_affiliation_strings":["Concordia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7577999830245972,"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":0.7577999830245972,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.07980000227689743,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05810000002384186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/secure-code-generation","display_name":"secure code generation","score":0.9919999837875366},{"id":"https://openalex.org/keywords/instruction-tuning-dataset","display_name":"instruction-tuning dataset","score":0.7149999737739563},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8349999785423279},{"id":"https://openalex.org/keywords/software-vulnerabilities","display_name":"software vulnerabilities","score":0.5879999995231628},{"id":"https://openalex.org/keywords/common-weakness-enumeration","display_name":"Common Weakness Enumeration","score":0.8539999723434448},{"id":"https://openalex.org/keywords/functional-correctness","display_name":"functional correctness","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7407000064849854},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5547999739646912},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.44200000166893005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.314300000667572},{"id":"https://openalex.org/C62913178","wikidata":"https://www.wikidata.org/wiki/Q7554361","display_name":"Software security assurance","level":4,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.07189","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07189","pdf_url":"https://arxiv.org/pdf/2510.07189","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07189","doi":"https://doi.org/10.48550/arxiv.2510.07189","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07189","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.07189","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07189","pdf_url":"https://arxiv.org/pdf/2510.07189","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415318208.pdf","grobid_xml":"https://content.openalex.org/works/W4415318208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166563475","https://openalex.org/W4400374531","https://openalex.org/W4403623850","https://openalex.org/W6928794810","https://openalex.org/W7130651357","https://openalex.org/W4415746230","https://openalex.org/W4416022645","https://openalex.org/W7128548217","https://openalex.org/W7162424107","https://openalex.org/W7103987345"],"abstract_inverted_index":{"Although":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"show":[5],"promising":[6],"solutions":[7],"to":[8,25,58],"automated":[9],"code":[10,16,28,53,64,122,130],"generation,":[11,131],"they":[12],"often":[13],"produce":[14],"insecure":[15],"that":[17,46,113],"threatens":[18],"software":[19],"security.":[20],"Current":[21],"approaches":[22],"(e.g.,":[23],"SafeCoder)":[24],"improve":[26],"secure":[27,52,63,129,139],"generation":[29,65],"are":[30],"limited":[31],"by":[32,148],"small,":[33],"imbalanced":[34],"instruction-tuning":[35,98],"datasets.":[36],"In":[37],"this":[38],"work,":[39],"we":[40],"present":[41],"Secure-Instruct,":[42],"a":[43,133],"novel":[44],"pipeline":[45],"automatically":[47],"synthesizes":[48],"high-quality":[49],"vulnerable":[50],"and":[51,55,62,81,118,145,160,169],"examples":[54],"instruction-tunes":[56],"LLMs":[57,73],"align":[59],"task":[60],"description":[61],"abilities.":[66],"We":[67,111],"evaluate":[68],"Secure-Instruct":[69,114,126,152],"on":[70,89,136],"four":[71],"representative":[72],"using":[74],"two":[75],"security-related":[76],"benchmarks:":[77],"our":[78],"own":[79],"CWEBench":[80,85],"the":[82,142],"existing":[83],"CWEval.":[84],"comprises":[86],"93":[87],"scenarios":[88],"44":[90],"CWEs,":[91],"all":[92],"without":[93],"overlap":[94],"with":[95,105],"Secure-Instruct's":[96],"synthetic":[97],"dataset,":[99],"while":[100],"CWEval":[101],"covers":[102],"31":[103],"CWEs":[104],"119":[106],"manually":[107],"verified":[108],"security-critical":[109],"tasks.":[110],"find":[112],"improves":[115,128],"both":[116],"security":[117],"functional":[119],"correctness":[120],"in":[121,138,164],"generation.":[123],"On":[124,150],"CWEBench,":[125],"substantially":[127],"giving":[132],"28.5%":[134],"increase":[135,155],"average":[137],"ratio":[140],"over":[141,166],"pre-trained":[143],"models":[144],"outperforms":[146,171],"SafeCoder":[147],"12.6%.":[149],"CWEval,":[151],"achieves":[153],"an":[154],"of":[156],"157.3%":[157],"for":[158,162],"CodeLlama-7B":[159],"46.4%":[161],"Mistral-7B":[163],"Func-Sec@1":[165],"pretrained":[167],"models,":[168],"significantly":[170],"SafeCoder.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}