{"id":"https://openalex.org/W4411088313","doi":"https://doi.org/10.1145/3713081.3732931","title":"Patch the Leak: Strengthening CodeLLMs Against Privacy Extraction Threats","display_name":"Patch the Leak: Strengthening CodeLLMs Against Privacy Extraction Threats","publication_year":2025,"publication_date":"2025-06-06","ids":{"openalex":"https://openalex.org/W4411088313","doi":"https://doi.org/10.1145/3713081.3732931"},"language":"en","primary_location":{"id":"doi:10.1145/3713081.3732931","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713081.3732931","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 34th ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3713081.3732931","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114173920","display_name":"Yongjian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Guo","raw_affiliation_strings":["Ant Group, Hangzhou, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-9279-3010","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011383481","display_name":"Wanlun Ma","orcid":"https://orcid.org/0000-0002-6305-1740"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanlun Ma","raw_affiliation_strings":["Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6305-1740","affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Xiao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1521-9542","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076576641","display_name":"Sheng Wen","orcid":"https://orcid.org/0000-0003-0655-666X"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sheng Wen","raw_affiliation_strings":["Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0655-666X","affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000833287","display_name":"Peng Di","orcid":"https://orcid.org/0000-0002-5799-5876"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peng Di","raw_affiliation_strings":["Ant Group, Hangzhou, China","UNSW Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5799-5876","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"UNSW Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015792635","display_name":"Xiaogang Zhu","orcid":"https://orcid.org/0000-0002-0647-4747"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaogang Zhu","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0647-4747","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16601799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.982699990272522,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.982699990272522,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9718999862670898,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9718000292778015,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.6436874270439148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.577850878238678},{"id":"https://openalex.org/keywords/leak","display_name":"Leak","score":0.5695115327835083},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"Privacy protection","score":0.5196005702018738},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.45856204628944397},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4376150667667389},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.41020703315734863},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.10480862855911255}],"concepts":[{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6436874270439148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.577850878238678},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.5695115327835083},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.5196005702018738},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.45856204628944397},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4376150667667389},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.41020703315734863},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.10480862855911255},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3713081.3732931","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713081.3732931","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 34th ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3713081.3732931","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713081.3732931","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 34th ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3168867926","https://openalex.org/W4307079201","https://openalex.org/W4378771755","https://openalex.org/W4386755323","https://openalex.org/W4391974554","https://openalex.org/W4393160410","https://openalex.org/W4399422490","https://openalex.org/W4407236106","https://openalex.org/W4408750038","https://openalex.org/W4409348010"],"related_works":["https://openalex.org/W2584827882","https://openalex.org/W3195097297","https://openalex.org/W3038106605","https://openalex.org/W2513267613","https://openalex.org/W3049084372","https://openalex.org/W2528109871","https://openalex.org/W2940702331","https://openalex.org/W2905822832","https://openalex.org/W4225340788","https://openalex.org/W4318485713"],"abstract_inverted_index":{"CodeLLMs":[0,47,115],"tend":[1],"to":[2,24,71,80,136,146,168,174],"memorize":[3],"their":[4],"training":[5,157],"data":[6],"and":[7,40,45,74,103,126],"can":[8],"reconstruct":[9],"personal":[10],"information":[11,51],"(PI)":[12],"when":[13],"given":[14],"specific":[15],"prompts.":[16],"Despite":[17],"the":[18,30,81,86,117,128,138,148],"application":[19],"of":[20,88,101],"privacy":[21],"anonymization":[22],"methods":[23],"remove":[25],"PI":[26,35,92,96,152,179],"in":[27],"foundational":[28],"LLMs,":[29],"previous":[31],"experiments":[32],"using":[33],"state-of-the-art":[34],"extraction":[36,153,180],"attacks":[37,154,181],"like":[38],"CODEBREAKER":[39,118],"CodexLeaks":[41],"on":[42,182],"multiple":[43],"open-source":[44,72],"commercial":[46,60],"demonstrate":[48],"that":[49,59],"such":[50],"cannot":[52],"be":[53],"fully":[54],"eliminated.":[55],"Furthermore,":[56],"we":[57,75,94],"found":[58],"models":[61],"exhibit":[62],"significantly":[63],"lower":[64],"leakage":[65,97],"rates":[66],"(approximately":[67],"20%":[68],"lower)":[69],"compared":[70],"models,":[73],"hypothesize":[76],"this":[77],"is":[78,144],"related":[79],"stronger":[82],"model":[83,125,139],"alignment.":[84],"Addressing":[85],"lack":[87],"effective":[89],"defenses":[90],"against":[91,151,159],"extraction,":[93],"treat":[95],"as":[98,121],"a":[99,106],"form":[100],"misalignment":[102],"propose":[104],"PI-ALIGN,":[105],"novel":[107],"framework":[108,120,167],"inspired":[109],"by":[110,155],"adversarial":[111,123],"learning.":[112],"PI-ALIGN":[113],"pairs":[114],"with":[116],"attack":[119],"an":[122],"dual":[124],"leverages":[127],"optimized":[129],"GRPO":[130],"(Group":[131],"Relative":[132],"Policy":[133],"Optimization)":[134],"process":[135],"realign":[137],"during":[140],"fine-tuning.":[141],"This":[142],"approach":[143],"expected":[145],"enhance":[147],"model's":[149],"robustness":[150],"adversarially":[156],"it":[158],"CODEBREAKER.":[160],"We":[161],"also":[162],"outline":[163],"our":[164],"experimental":[165],"evaluation":[166],"systematically":[169],"validate":[170],"PI-ALIGN's":[171],"effectiveness,":[172],"aiming":[173],"provide":[175],"insights":[176],"into":[177],"countering":[178],"CodeLLMs.":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}