{"id":"https://openalex.org/W7167428808","doi":"https://doi.org/10.1145/3805760.3814902","title":"When AI Coding Assistants Leak Training Data: A Study of LLM Memorization in Code Generation","display_name":"When AI Coding Assistants Leak Training Data: A Study of LLM Memorization in Code Generation","publication_year":2026,"publication_date":"2026-07-05","ids":{"openalex":"https://openalex.org/W7167428808","doi":"https://doi.org/10.1145/3805760.3814902"},"language":null,"primary_location":{"id":"doi:10.1145/3805760.3814902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814902","pdf_url":null,"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 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805760.3814902","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102984455","display_name":"Xiaoyu Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaoyu Cheng","raw_affiliation_strings":["University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada"],"raw_orcid":"https://orcid.org/0009-0007-9958-5836","affiliations":[{"raw_affiliation_string":"University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035956071","display_name":"Kundi Yao","orcid":"https://orcid.org/0000-0002-3756-4673"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"Ontario Tech University","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kundi Yao","raw_affiliation_strings":["Ontario Tech University, Faculty of Engineering and Applied Science, Oshawa, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3756-4673","affiliations":[{"raw_affiliation_string":"Ontario Tech University, Faculty of Engineering and Applied Science, Oshawa, Canada","institution_ids":["https://openalex.org/I39470171"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043609524","display_name":"Pengyu Nie","orcid":"https://orcid.org/0000-0003-1529-3216"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pengyu Nie","raw_affiliation_strings":["University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1529-3216","affiliations":[{"raw_affiliation_string":"University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056378414","display_name":"Weiyi Shang","orcid":"https://orcid.org/0000-0001-6222-7444"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiyi Shang","raw_affiliation_strings":["University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6222-7444","affiliations":[{"raw_affiliation_string":"University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.517799973487854,"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":0.517799973487854,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.05270000174641609,"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/memorization","display_name":"Memorization","score":0.9469000101089478},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6488999724388123},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6370999813079834},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47609999775886536},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3736000061035156}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.9469000101089478},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269000172615051},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4587000012397766},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805760.3814902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814902","pdf_url":null,"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 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805760.3814902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805760.3814902","pdf_url":null,"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 3rd ACM International Conference on AI-Powered Software","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.48758354783058167}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2003986132","https://openalex.org/W2344444819","https://openalex.org/W2535690855","https://openalex.org/W2946930197","https://openalex.org/W3118781290","https://openalex.org/W4287077924","https://openalex.org/W4287553002","https://openalex.org/W4288331677","https://openalex.org/W4311887664","https://openalex.org/W4321175641","https://openalex.org/W4387355380","https://openalex.org/W4391901270","https://openalex.org/W4392019445","https://openalex.org/W4394744221","https://openalex.org/W4394745382","https://openalex.org/W4399759467","https://openalex.org/W4401306886","https://openalex.org/W4403370452","https://openalex.org/W4404570405","https://openalex.org/W4406975467","https://openalex.org/W4413176572","https://openalex.org/W4415957649","https://openalex.org/W4417068181","https://openalex.org/W6967084484","https://openalex.org/W7133237827"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"for":[4,119],"code":[5,16,29,100,106],"generation":[6,30],"risk":[7],"memorizing":[8],"and":[9,17,56,148,163],"reproducing":[10],"sensitive":[11],"training":[12,157],"data,":[13],"including":[14],"licensed":[15],"proprietary":[18],"information.":[19],"We":[20,49,123],"investigate":[21],"memorization":[22,34,69,111,143],"behavior":[23],"in":[24,28,112,145],"recent":[25],"open-weight":[26],"LLMs":[27,147],"using":[31],"a":[32,39,44,59,135,153],"two-stage":[33],"evaluation":[35],"pipeline,":[36],"which":[37],"combines":[38],"similarity-based":[40],"extractability":[41],"filter":[42],"with":[43,73],"targeted":[45],"data":[46],"extraction":[47,129],"attack.":[48],"evaluate":[50],"four":[51],"models":[52,75],"(StarCoder2-3B,":[53],"StarCoder2-7B,":[54],"Llama3-8B,":[55],"DeepSeek-R1-distilled-Llama-8B)":[57],"on":[58],"custom":[60],"dataset":[61,159],"of":[62,71,114,156],"30,000+":[63],"Python":[64],"files.":[65],"Our":[66,139],"results":[67],"reveal":[68],"rates":[70,78,94,130],"42-64%,":[72],"code-specialized":[74],"exhibiting":[76],"higher":[77],"than":[79,167],"general-purpose":[80],"models.":[81],"Categorical":[82],"analysis":[83],"shows":[84],"that":[85,125,142],"repetitive":[86],"content":[87,164],"(license":[88],"headers,":[89],"documentation)":[90],"is":[91,149],"memorized":[92],"at":[93],"up":[95],"to":[96],"70%,":[97],"while":[98],"complex":[99,154],"exhibits":[101],"lower":[102],"susceptibility.":[103],"Notably,":[104],"realistic":[105],"completion":[107],"scenarios":[108],"trigger":[109],"unintentional":[110],"13-14%":[113],"cases,":[115],"posing":[116],"practical":[117],"risks":[118],"AI":[120],"coding":[121],"assistants.":[122],"demonstrate":[124],"knowledge":[126],"distillation":[127],"reduces":[128],"by":[131,152],"approximately":[132],"19%,":[133],"offering":[134],"cost-effective":[136],"mitigation":[137],"approach.":[138],"findings":[140],"confirm":[141],"persists":[144],"modern":[146],"influenced":[150],"more":[151],"interplay":[155],"domain,":[158],"composition,":[160],"architectural":[161],"choices,":[162],"characteristics,":[165],"rather":[166],"parameter":[168],"count":[169],"alone.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-06T00:00:00"}