{"id":"https://openalex.org/W4386272920","doi":"https://doi.org/10.1145/3611643.3616297","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","display_name":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4386272920","doi":"https://doi.org/10.1145/3611643.3616297"},"language":"en","primary_location":{"id":"doi:10.1145/3611643.3616297","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.14401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078038118","display_name":"Zhensu Sun","orcid":"https://orcid.org/0000-0001-5393-7858"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhensu Sun","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5393-7858","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102717874","display_name":"Xiaoning Du","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoning Du","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3728-9541","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027425633","display_name":"Fu Song","orcid":"https://orcid.org/0000-0002-0581-2679"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Song","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China / University of Chinese Academy of Sciences, Beijing, China / Automotive Software Innovation Center, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-0581-2679","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China / University of Chinese Academy of Sciences, Beijing, China / Automotive Software Innovation Center, Chongqing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106407830","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-2990-1614"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2990-1614","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078038118"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":4.4306,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9559466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1561","last_page":"1572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9921000003814697,"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/T10260","display_name":"Software Engineering Research","score":0.9667999744415283,"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-science","display_name":"Computer science","score":0.8469105362892151},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6920729875564575},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5485115051269531},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.5156611204147339},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.5012245178222656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46337902545928955},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4485104978084564},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4236864447593689},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.386213481426239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38206490874290466},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3340412378311157},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3128567337989807},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19222167134284973},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12799474596977234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469105362892151},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6920729875564575},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5485115051269531},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.5156611204147339},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.5012245178222656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46337902545928955},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4485104978084564},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4236864447593689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.386213481426239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38206490874290466},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3340412378311157},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3128567337989807},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19222167134284973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12799474596977234},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3611643.3616297","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.14401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14401","pdf_url":"https://arxiv.org/pdf/2308.14401","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.14401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14401","pdf_url":"https://arxiv.org/pdf/2308.14401","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G450653452","display_name":null,"funder_award_id":"62072309","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4677120484","display_name":null,"funder_award_id":"YSBR-040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386272920.pdf","grobid_xml":"https://content.openalex.org/works/W4386272920.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W160164572","https://openalex.org/W2034196543","https://openalex.org/W2101105183","https://openalex.org/W2108320571","https://openalex.org/W2109471780","https://openalex.org/W2113757735","https://openalex.org/W2350778671","https://openalex.org/W2931043484","https://openalex.org/W2997451752","https://openalex.org/W3109966548","https://openalex.org/W3127882434","https://openalex.org/W3129468510","https://openalex.org/W3131641316","https://openalex.org/W3154734736","https://openalex.org/W3155146092","https://openalex.org/W3170572542","https://openalex.org/W4221086183","https://openalex.org/W4224307896","https://openalex.org/W4300007223"],"related_works":["https://openalex.org/W2137394636","https://openalex.org/W2358993821","https://openalex.org/W1516446231","https://openalex.org/W2098152888","https://openalex.org/W1559740347","https://openalex.org/W2040356834","https://openalex.org/W2080353903","https://openalex.org/W2385289568","https://openalex.org/W2381486749","https://openalex.org/W1514507288"],"abstract_inverted_index":{"Code":[0],"datasets":[1,138],"are":[2,97],"of":[3,40,55,85,108,114,161,183,195],"immense":[4],"value":[5],"for":[6,31,62],"training":[7,67,144],"neural-network-based":[8],"code":[9,102,115,137,146,163,184],"completion":[10,147,185],"models,":[11],"where":[12],"companies":[13],"or":[14,33],"organizations":[15],"have":[16,78],"made":[17],"substantial":[18],"investments":[19],"to":[20,64,81,93,101,119,131,139,190,200],"establish":[21],"and":[22,87,111,165,178,205],"process":[23],"these":[24,27,72],"datasets.":[25,90],"Unluckily,":[26],"datasets,":[28,68,103],"either":[29],"built":[30],"proprietary":[32],"public":[34],"usage,":[35],"face":[36],"the":[37,52,105,158,162,167],"high":[38,60],"risk":[39],"unauthorized":[41,73],"exploits,":[42],"resulting":[43],"from":[44],"data":[45,116,164],"leakages,":[46],"license":[47],"violations,":[48],"etc.":[49],"Even":[50],"worse,":[51],"\"black-box\"":[53],"nature":[54],"neural":[56,145],"models":[57],"sets":[58],"a":[59,127,176],"barrier":[61],"externals":[63],"audit":[65],"their":[66,141],"which":[69,156],"further":[70],"connives":[71],"usages.":[74],"Currently,":[75],"watermarking":[76],"methods":[77],"been":[79],"proposed":[80],"prohibit":[82],"inappropriate":[83],"usage":[84,142],"image":[86],"natural":[88],"language":[89],"However,":[91],"due":[92],"domain":[94],"specificity,":[95],"they":[96],"not":[98],"directly":[99],"applicable":[100],"leaving":[104],"copyright":[106],"protection":[107],"this":[109,123],"emerging":[110],"important":[112],"field":[113],"still":[117],"exposed":[118],"threats.":[120],"To":[121],"fill":[122],"gap,":[124],"we":[125],"propose":[126],"method,":[128],"named":[129],"CodeMark,":[130],"embed":[132],"user-defined":[133],"imperceptible":[134],"watermarks":[135],"into":[136],"trace":[140],"in":[143,175],"models.":[148,186],"CodeMark":[149,174,187],"is":[150,188],"based":[151],"on":[152],"adaptive":[153],"semantic-preserving":[154],"transformations,":[155],"preserve":[157],"exact":[159],"functionality":[160],"keep":[166],"changes":[168],"covert":[169],"against":[170],"rule-breakers.":[171],"We":[172],"implement":[173],"toolkit":[177],"conduct":[179],"an":[180],"extensive":[181],"evaluation":[182],"validated":[189],"fulfill":[191],"all":[192],"desired":[193],"properties":[194],"practical":[196],"watermarks,":[197],"including":[198],"harmlessness":[199],"model":[201],"accuracy,":[202],"verifiability,":[203],"robustness,":[204],"imperceptibility.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}