{"id":"https://openalex.org/W4319451764","doi":"https://doi.org/10.1109/tse.2023.3240118","title":"Challenging Machine Learning-Based Clone Detectors via Semantic-Preserving Code Transformations","display_name":"Challenging Machine Learning-Based Clone Detectors via Semantic-Preserving Code Transformations","publication_year":2023,"publication_date":"2023-01-27","ids":{"openalex":"https://openalex.org/W4319451764","doi":"https://doi.org/10.1109/tse.2023.3240118"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2023.3240118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3240118","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5100446744","display_name":"Weiwei Zhang","orcid":"https://orcid.org/0000-0002-4304-6055"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-4304-6055","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015125413","display_name":"Shengjian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjian Guo","raw_affiliation_strings":["Baidu Security, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Security, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["University of Newcastle, Callaghan, NSW, Australia","Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-3063-9425","affiliations":[{"raw_affiliation_string":"University of Newcastle, Callaghan, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]},{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053058502","display_name":"Yulei Sui","orcid":"https://orcid.org/0000-0002-9510-6574"},"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":"Yulei Sui","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083669929","display_name":"Yinxing Xue","orcid":"https://orcid.org/0000-0002-2979-7151"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinxing Xue","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-2979-7151","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105471307","display_name":"Yun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.4412,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.99107802,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"49","issue":"5","first_page":"3052","last_page":"3070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9973000288009644,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8229749202728271},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.602249801158905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001833081245422},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5888336896896362},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5600143671035767},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5371793508529663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5078752636909485},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.438755601644516},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.42054125666618347},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.42016321420669556},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4080510139465332},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39959174394607544},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11048147082328796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229749202728271},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.602249801158905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001833081245422},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5888336896896362},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5600143671035767},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5371793508529663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5078752636909485},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.438755601644516},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.42054125666618347},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.42016321420669556},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4080510139465332},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39959174394607544},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11048147082328796},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2023.3240118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2023.3240118","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3988094133","display_name":"\u57fa\u4e8e\u5dee\u5f02\u6bd4\u8f83\u4ee5\u653b\u51fb\u9762\u4e3a\u5bfc\u5411\u7684\u7070\u76d2\u6a21\u7cca\u6d4b\u8bd5\u7cfb\u7edf\u7814\u7a76","funder_award_id":"61972373","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5954519879","display_name":null,"funder_award_id":"BK20201192","funder_id":"https://openalex.org/F4320334982","funder_display_name":"Basic Research Program of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334982","display_name":"Basic Research Program of Jiangsu Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W189129979","https://openalex.org/W1485009520","https://openalex.org/W1543331277","https://openalex.org/W1559956479","https://openalex.org/W1574901103","https://openalex.org/W1777239053","https://openalex.org/W1979852787","https://openalex.org/W1999404243","https://openalex.org/W2001496424","https://openalex.org/W2010515683","https://openalex.org/W2025962632","https://openalex.org/W2065053490","https://openalex.org/W2084201645","https://openalex.org/W2090432523","https://openalex.org/W2100060170","https://openalex.org/W2101832700","https://openalex.org/W2104301886","https://openalex.org/W2107697055","https://openalex.org/W2111295912","https://openalex.org/W2115534035","https://openalex.org/W2119538795","https://openalex.org/W2120319185","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2132944054","https://openalex.org/W2135841285","https://openalex.org/W2138756793","https://openalex.org/W2145339207","https://openalex.org/W2148646465","https://openalex.org/W2155007355","https://openalex.org/W2157532207","https://openalex.org/W2158439356","https://openalex.org/W2163225748","https://openalex.org/W2165739648","https://openalex.org/W2178906754","https://openalex.org/W2257979135","https://openalex.org/W2282866165","https://openalex.org/W2427333829","https://openalex.org/W2486765974","https://openalex.org/W2511803001","https://openalex.org/W2584966780","https://openalex.org/W2618879712","https://openalex.org/W2634106992","https://openalex.org/W2736601468","https://openalex.org/W2741705590","https://openalex.org/W2762536380","https://openalex.org/W2766078762","https://openalex.org/W2766447205","https://openalex.org/W2767717989","https://openalex.org/W2777616600","https://openalex.org/W2786944871","https://openalex.org/W2793776506","https://openalex.org/W2794304550","https://openalex.org/W2794744252","https://openalex.org/W2808509424","https://openalex.org/W2883359218","https://openalex.org/W2899171197","https://openalex.org/W2904067867","https://openalex.org/W2919074952","https://openalex.org/W2921323488","https://openalex.org/W2940499664","https://openalex.org/W2954552517","https://openalex.org/W2955426500","https://openalex.org/W2996739384","https://openalex.org/W2997451752","https://openalex.org/W3006491415","https://openalex.org/W3012514498","https://openalex.org/W3031788714","https://openalex.org/W3035328655","https://openalex.org/W3043078865","https://openalex.org/W3045279034","https://openalex.org/W3091995628","https://openalex.org/W3100161332","https://openalex.org/W3108623714","https://openalex.org/W3125205154","https://openalex.org/W3125675786","https://openalex.org/W3146720657","https://openalex.org/W3166956180","https://openalex.org/W3215498156","https://openalex.org/W4211221179","https://openalex.org/W4241674441","https://openalex.org/W4255660245","https://openalex.org/W4287828464","https://openalex.org/W4301168982","https://openalex.org/W4394664141","https://openalex.org/W6632523919","https://openalex.org/W6638088447","https://openalex.org/W6682849425","https://openalex.org/W6741002519","https://openalex.org/W6744628271","https://openalex.org/W6774537256","https://openalex.org/W6804347171","https://openalex.org/W6864870587"],"related_works":["https://openalex.org/W2377327490","https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W3081644756","https://openalex.org/W3122369893","https://openalex.org/W2407476586","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W2750654225","https://openalex.org/W1977905671"],"abstract_inverted_index":{"Software":[0],"clone":[1,42,75,199,225],"detection":[2,259],"identifies":[3],"similar":[4],"or":[5],"identical":[6],"code":[7,78,86,177,215,254],"snippets.":[8],"It":[9,44],"has":[10,50,247],"been":[11,52],"an":[12,268],"active":[13],"research":[14],"topic":[15],"that":[16,46,128],"attracts":[17],"extensive":[18],"attention":[19,285],"over":[20],"the":[21,56,69,72,122,132,137,141,166,176,183,193,201,214,241,244,249,258,262,276,287],"last":[22],"two":[23],"decades.":[24],"In":[25,61,162,219],"recent":[26,73],"years,":[27],"machine":[28],"learning":[29],"(ML)":[30],"based":[31],"detectors,":[32,200],"especially":[33],"deep":[34,112],"learning-based":[35,114],"ones,":[36],"have":[37],"demonstrated":[38],"impressive":[39],"capability":[40],"on":[41],"detection.":[43,133],"seems":[45],"this":[47,62],"longstanding":[48],"problem":[49],"already":[51],"tamed":[53],"owing":[54],"to":[55,67,103,119,256,286],"advances":[57],"in":[58,152,217,252],"ML":[59,202],"techniques.":[60],"work,":[63],"we":[64,109,164,281],"would":[65],"like":[66],"challenge":[68,165],"robustness":[70,235,273,288],"of":[71,125,143,185,223,261,275,289],"ML-based":[74,138,169,224,263,278,292],"detectors":[76,139,170,174,206,226],"through":[77],"semantic-preserving":[79,180],"transformations.":[80],"We":[81,134,148],"first":[82],"utilize":[83],"fifteen":[84],"simple":[85],"transformation":[87],"operators":[88],"combined":[89],"with":[90,140,175,240],"commonly-used":[91,242],"heuristics":[92],"(i.e.,":[93],"Random":[94],"Search,":[95],"Genetic":[96],"Algorithm,":[97],"and":[98,145,171,236],"Markov":[99],"Chain":[100],"Monte":[101],"Carlo)":[102],"perform":[104],"equivalent":[105],"program":[106],"transformation.":[107],"Furthermore,":[108],"propose":[110],"a":[111,153],"reinforcement":[113],"sequence":[115],"generation":[116],"(DRLSG)":[117],"strategy":[118,246],"effectively":[120],"guide":[121],"search":[123],"process":[124],"generating":[126,253],"clones":[127,178,211,228,255],"could":[129],"escape":[130],"from":[131],"then":[135],"evaluate":[136],"pairs":[142],"original":[144],"generated":[146,229],"clones.":[147],"realize":[149],"our":[150,188],"method":[151],"framework":[154],"named":[155],"CloneGen":[156,161,231],"(stands":[157],"for":[158,283],"Clone":[159],"Generator).":[160],"evaluation,":[163],"three":[167],"state-of-the-art":[168],"four":[172],"traditional":[173],"after":[179],"transformations":[181,216],"via":[182],"aid":[184],"CloneGen.":[186,218],"Surprisingly,":[187],"experiments":[189],"show":[190],"that,":[191],"despite":[192],"notable":[194],"successes":[195],"achieved":[196],"by":[197,213,230],"existing":[198],"models":[203],"inside":[204],"these":[205,290],"still":[207],"cannot":[208],"distinguish":[209],"numerous":[210],"produced":[212],"addition,":[220],"adversarial":[221],"training":[222],"using":[227],"can":[232],"improve":[233],"their":[234],"accuracy.":[237],"Meanwhile,":[238],"compared":[239],"heuristics,":[243],"DRLSG":[245],"shown":[248],"best":[250],"effectiveness":[251],"decrease":[257],"accuracy":[260],"detectors.":[264,279,293],"Our":[265],"investigation":[266],"reveals":[267],"explicable":[269],"but":[270],"always":[271],"ignored":[272],"issue":[274],"latest":[277],"Therefore,":[280],"call":[282],"more":[284],"new":[291]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}