{"id":"https://openalex.org/W4417164108","doi":"https://doi.org/10.1016/j.jss.2025.112729","title":"Peeking inside the black box: Training data exposure in code language models","display_name":"Peeking inside the black box: Training data exposure in code language models","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4417164108","doi":"https://doi.org/10.1016/j.jss.2025.112729"},"language":"en","primary_location":{"id":"doi:10.1016/j.jss.2025.112729","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jss.2025.112729","pdf_url":null,"source":{"id":"https://openalex.org/S37879656","display_name":"Journal of Systems and Software","issn_l":"0164-1212","issn":["0164-1212","1873-1228"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems and Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107104004","display_name":"Angelica Spina","orcid":"https://orcid.org/0009-0001-6904-6184"},"institutions":[{"id":"https://openalex.org/I129627893","display_name":"University of Molise","ror":"https://ror.org/04z08z627","country_code":"IT","type":"education","lineage":["https://openalex.org/I129627893"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angelica Spina","raw_affiliation_strings":["University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy"],"raw_orcid":"https://orcid.org/0009-0001-6904-6184","affiliations":[{"raw_affiliation_string":"University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy","institution_ids":["https://openalex.org/I129627893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046046002","display_name":"Marco Russodivito","orcid":null},"institutions":[{"id":"https://openalex.org/I129627893","display_name":"University of Molise","ror":"https://ror.org/04z08z627","country_code":"IT","type":"education","lineage":["https://openalex.org/I129627893"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Russodivito","raw_affiliation_strings":["University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy"],"raw_orcid":"https://orcid.org/0009-0004-8860-1739","affiliations":[{"raw_affiliation_string":"University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy","institution_ids":["https://openalex.org/I129627893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079406478","display_name":"Simone Scalabrino","orcid":"https://orcid.org/0000-0003-1764-9685"},"institutions":[{"id":"https://openalex.org/I129627893","display_name":"University of Molise","ror":"https://ror.org/04z08z627","country_code":"IT","type":"education","lineage":["https://openalex.org/I129627893"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Scalabrino","raw_affiliation_strings":["University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1764-9685","affiliations":[{"raw_affiliation_string":"University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy","institution_ids":["https://openalex.org/I129627893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009727039","display_name":"Rocco Oliveto","orcid":"https://orcid.org/0000-0002-7995-8582"},"institutions":[{"id":"https://openalex.org/I129627893","display_name":"University of Molise","ror":"https://ror.org/04z08z627","country_code":"IT","type":"education","lineage":["https://openalex.org/I129627893"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Rocco Oliveto","raw_affiliation_strings":["University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7995-8582","affiliations":[{"raw_affiliation_string":"University of Molise, Contrada Fonte Lappone, Pesche (IS), 86090, Italy","institution_ids":["https://openalex.org/I129627893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009727039"],"corresponding_institution_ids":["https://openalex.org/I129627893"],"apc_list":{"value":3560,"currency":"USD","value_usd":3560},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20054681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"234","issue":null,"first_page":"112729","last_page":"112729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5612999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5612999796867371,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.22460000216960907,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.8363000154495239},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5490000247955322},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5428000092506409},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.4875999987125397},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4722000062465668},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.46880000829696655}],"concepts":[{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.8363000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376000285148621},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.jss.2025.112729","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.jss.2025.112729","pdf_url":null,"source":{"id":"https://openalex.org/S37879656","display_name":"Journal of Systems and Software","issn_l":"0164-1212","issn":["0164-1212","1873-1228"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems and Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2356585098","display_name":null,"funder_award_id":"PE00000014","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G4820512824","display_name":null,"funder_award_id":"H73C22000890001","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G4998521255","display_name":null,"funder_award_id":"B43C22000750006","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G5634975520","display_name":null,"funder_award_id":"H53D23003520006","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320331528","display_name":"Ministero dell'Universit\u00e0 e della Ricerca","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3043638540","https://openalex.org/W3198685994","https://openalex.org/W4317796234","https://openalex.org/W4384499025","https://openalex.org/W4385572432","https://openalex.org/W4389519352","https://openalex.org/W4392023437","https://openalex.org/W4397006720","https://openalex.org/W4405894420","https://openalex.org/W4410290121","https://openalex.org/W4411271534"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-12-09T00:00:00"}
