{"id":"https://openalex.org/W2138812986","doi":"https://doi.org/10.1016/j.entcs.2009.09.040","title":"Finding Similarities in Source Code Through Factorization","display_name":"Finding Similarities in Source Code Through Factorization","publication_year":2009,"publication_date":"2009-09-30","ids":{"openalex":"https://openalex.org/W2138812986","doi":"https://doi.org/10.1016/j.entcs.2009.09.040","mag":"2138812986"},"language":"en","primary_location":{"id":"doi:10.1016/j.entcs.2009.09.040","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.entcs.2009.09.040","pdf_url":null,"source":{"id":"https://openalex.org/S50368787","display_name":"Electronic Notes in Theoretical Computer Science","issn_l":"1571-0661","issn":["1571-0661"],"is_oa":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Notes in Theoretical Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.entcs.2009.09.040","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042865519","display_name":"Michel Chilowicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Michel Chilowicz","raw_affiliation_strings":["Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071886522","display_name":"\u00c9tienne Duris","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"\u00c9tienne Duris","raw_affiliation_strings":["Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037869012","display_name":"Gilles Roussel","orcid":"https://orcid.org/0000-0002-8531-1566"},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gilles Roussel","raw_affiliation_strings":["Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Est, Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037869012","https://openalex.org/A5042865519","https://openalex.org/A5071886522"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210152518"],"apc_list":null,"apc_paid":null,"fwci":2.1148,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87471249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"238","issue":"5","first_page":"47","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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/T10260","display_name":"Software Engineering Research","score":0.9966999888420105,"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":0.8439319133758545},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.6456024646759033},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6072194576263428},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5619164109230042},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.5292182564735413},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5188809037208557},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.499483585357666},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43679118156433105},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42218124866485596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3317989706993103},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3027426600456238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11228495836257935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439319133758545},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.6456024646759033},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6072194576263428},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5619164109230042},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.5292182564735413},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5188809037208557},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.499483585357666},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43679118156433105},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42218124866485596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3317989706993103},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3027426600456238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11228495836257935},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.entcs.2009.09.040","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.entcs.2009.09.040","pdf_url":null,"source":{"id":"https://openalex.org/S50368787","display_name":"Electronic Notes in Theoretical Computer Science","issn_l":"1571-0661","issn":["1571-0661"],"is_oa":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Notes in Theoretical Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.entcs.2009.09.040","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.entcs.2009.09.040","pdf_url":null,"source":{"id":"https://openalex.org/S50368787","display_name":"Electronic Notes in Theoretical Computer Science","issn_l":"1571-0661","issn":["1571-0661"],"is_oa":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Notes in Theoretical Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W58323294","https://openalex.org/W1507039213","https://openalex.org/W1809911053","https://openalex.org/W1969173824","https://openalex.org/W1972418517","https://openalex.org/W1984983703","https://openalex.org/W1990206024","https://openalex.org/W2030962049","https://openalex.org/W2092483417","https://openalex.org/W2096491586","https://openalex.org/W2107745473","https://openalex.org/W2109943392","https://openalex.org/W2111295912","https://openalex.org/W2120319185","https://openalex.org/W2128698639","https://openalex.org/W2130564474","https://openalex.org/W2145009222","https://openalex.org/W2146659255","https://openalex.org/W2149182189","https://openalex.org/W2157532207","https://openalex.org/W2158874082","https://openalex.org/W2166901988","https://openalex.org/W2752885492","https://openalex.org/W2947000318","https://openalex.org/W3004540582","https://openalex.org/W4205765539","https://openalex.org/W4372046852","https://openalex.org/W6638670089","https://openalex.org/W6657543964","https://openalex.org/W6658296292"],"related_works":["https://openalex.org/W4224216661","https://openalex.org/W3210347767","https://openalex.org/W98994209","https://openalex.org/W67940504","https://openalex.org/W2066014542","https://openalex.org/W2024170198","https://openalex.org/W2152144666","https://openalex.org/W1819617256","https://openalex.org/W4308699695","https://openalex.org/W2810872891"],"abstract_inverted_index":{"The":[0],"high":[1],"availability":[2],"of":[3,7,23,79,89,101],"a":[4,59],"huge":[5],"number":[6],"documents":[8],"on":[9,76,83,107],"the":[10,77],"Web":[11],"makes":[12],"plagiarism":[13,19],"very":[14],"attractive":[15],"and":[16,46,81,87,99,110,116],"easy.":[17],"This":[18,91],"concerns":[20],"any":[21],"kind":[22],"document,":[24],"natural":[25],"language":[26],"texts":[27],"as":[28,30,35,119],"well":[29],"more":[31],"structured":[32],"information":[33],"such":[34,118],"programs.":[36],"In":[37,54],"order":[38],"to":[39,51,63,70],"cope":[40],"with":[41,85],"this":[42,55,73],"problem,":[43],"many":[44],"tools":[45],"algorithms":[47,115],"have":[48],"been":[49],"proposed":[50],"find":[52],"similarities.":[53],"paper":[56],"we":[57],"present":[58],"new":[60],"algorithm":[61,74],"designed":[62],"detect":[64],"similarities":[65],"in":[66],"source":[67],"codes.":[68],"Contrary":[69],"existing":[71],"methods,":[72],"relies":[75],"notion":[78],"function":[80],"focuses":[82],"obfuscation":[84],"inlining":[86],"outlining":[88],"functions.":[90],"method":[92],"is":[93,105],"also":[94],"efficient":[95],"against":[96],"insertions,":[97],"deletions":[98],"permutations":[100],"instruction":[102],"blocks.":[103],"It":[104],"based":[106],"code":[108],"factorization":[109],"uses":[111],"adapted":[112],"pattern":[113],"matching":[114],"structures":[117],"suffix":[120],"arrays.":[121]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
