{"id":"https://openalex.org/W4405200152","doi":"https://doi.org/10.1145/3698062.3698087","title":"Comparison of Similarity Functions for n-gram Software Birthmarks","display_name":"Comparison of Similarity Functions for n-gram Software Birthmarks","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4405200152","doi":"https://doi.org/10.1145/3698062.3698087"},"language":"en","primary_location":{"id":"doi:10.1145/3698062.3698087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698062.3698087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 The 6th World Symposium on Software Engineering (WSSE)","raw_type":"proceedings-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/A5004258171","display_name":"Nikolay Fedorov","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nikolay Fedorov","raw_affiliation_strings":["Graduate School of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan"],"raw_orcid":"https://orcid.org/0009-0005-0310-5881","affiliations":[{"raw_affiliation_string":"Graduate School of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025715018","display_name":"Haruaki Tamada","orcid":"https://orcid.org/0000-0003-1838-9184"},"institutions":[{"id":"https://openalex.org/I168356945","display_name":"Kyoto Sangyo University","ror":"https://ror.org/05t70xh16","country_code":"JP","type":"education","lineage":["https://openalex.org/I168356945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruaki Tamada","raw_affiliation_strings":["Faculty of Information Science and Engineering, Kyoto Sangyo University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1838-9184","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Kyoto Sangyo University, Kyoto, Japan","institution_ids":["https://openalex.org/I168356945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075037207","display_name":"Hiroki Inayoshi","orcid":"https://orcid.org/0000-0003-3355-8804"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Inayoshi","raw_affiliation_strings":["Faculty of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3355-8804","affiliations":[{"raw_affiliation_string":"Faculty of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078686662","display_name":"Akito Monden","orcid":"https://orcid.org/0000-0003-4295-207X"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akito Monden","raw_affiliation_strings":["Faculty of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4295-207X","affiliations":[{"raw_affiliation_string":"Faculty of Environmental, Life, Natural Science and Technology, Okayama University, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004258171"],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":0.746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80903012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9991000294685364,"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":0.9933000206947327,"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/birthmark","display_name":"Birthmark","score":0.9385432600975037},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6872340440750122},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.6311952471733093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6021268963813782},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46637895703315735},{"id":"https://openalex.org/keywords/exception-handling","display_name":"Exception handling","score":0.4242340326309204},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2389332354068756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20245519280433655},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11601459980010986},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06447795033454895},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0585862398147583},{"id":"https://openalex.org/keywords/dermatology","display_name":"Dermatology","score":0.05555424094200134}],"concepts":[{"id":"https://openalex.org/C2776826570","wikidata":"https://www.wikidata.org/wiki/Q3513591","display_name":"Birthmark","level":2,"score":0.9385432600975037},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6872340440750122},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.6311952471733093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021268963813782},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46637895703315735},{"id":"https://openalex.org/C145428669","wikidata":"https://www.wikidata.org/wiki/Q471748","display_name":"Exception handling","level":2,"score":0.4242340326309204},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2389332354068756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20245519280433655},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11601459980010986},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06447795033454895},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0585862398147583},{"id":"https://openalex.org/C16005928","wikidata":"https://www.wikidata.org/wiki/Q171171","display_name":"Dermatology","level":1,"score":0.05555424094200134},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698062.3698087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698062.3698087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 The 6th World Symposium on Software Engineering (WSSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1500616534","https://openalex.org/W1863385414","https://openalex.org/W1985205072","https://openalex.org/W1995739251","https://openalex.org/W2010452235","https://openalex.org/W2086968222","https://openalex.org/W2101830524","https://openalex.org/W2108320571","https://openalex.org/W2136833842","https://openalex.org/W2146567535","https://openalex.org/W2151505086","https://openalex.org/W2194609298","https://openalex.org/W2475169603","https://openalex.org/W2611899778","https://openalex.org/W2908865399","https://openalex.org/W4292014584","https://openalex.org/W6639091781","https://openalex.org/W6681648988"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2789473152","https://openalex.org/W3027371124"],"abstract_inverted_index":{"Various":[0],"software":[1,8,17,59,85,101,157],"birthmarks":[2,47,98],"have":[3,19],"been":[4],"proposed":[5],"to":[6,77,202],"detect":[7],"plagiarism":[9],"or":[10],"unauthorized":[11],"reuse":[12],"of":[13,25,36,63,81,127,154,160,200],"code.":[14,180,205],"If":[15],"two":[16,84,100],"products":[18,60,86,102],"very":[20],"similar":[21],"birthmarks,":[22,123,131,191],"the":[23,34,42,49,79,113,121,128,148,195],"existence":[24],"reused":[26,38,53,172,179,204],"code":[27,39,173],"between":[28,83,99],"them":[29],"is":[30,87,125],"strongly":[31],"suspected.":[32],"However,":[33],"accuracy":[35],"detecting":[37],"depends":[40],"on":[41,120],"similarity":[43,136],"function":[44],"for":[45,51,96,111,115,186],"comparing":[46,97],"and":[48,54,71,144,174,189],"threshold":[50,114],"distinguishing":[52,116],"non-reused":[55],"codes.":[56],"Moreover,":[57],"since":[58],"usually":[61],"consist":[62],"many":[64,104],"program":[65],"modules":[66,82],"such":[67],"as":[68,106,108],"source":[69],"files":[70],"class":[72],"files,":[73],"an":[74],"appropriate":[75],"method":[76,95,110],"compare":[78,134],"set":[80],"needed.":[88],"In":[89,147],"this":[90],"paper":[91],"we":[92,132,150],"propose":[93],"a":[94,109],"containing":[103],"modules,":[105],"well":[107],"determining":[112],"reuse.":[117],"Afterwards,":[118],"focusing":[119],"n-gram":[122],"which":[124],"one":[126],"most":[129],"easy-to-measure":[130],"empirically":[133],"4":[135],"functions:":[137],"cosine":[138],"similarity,":[139],"Dice":[140],"index,":[141],"Jaccard":[142,192],"coefficient":[143,193],"Simpson":[145],"index.":[146],"experiment,":[149],"employ":[151],"multiple":[152],"versions":[153],"15":[155],"open-source":[156],"(OSS)":[158],"projects":[159],"5":[161],"categories,":[162],"making":[163],"sure":[164],"that":[165,170,175],"they":[166],"contain":[167,171,178],"project":[168],"pairs":[169],"do":[176],"not":[177],"The":[181],"experimental":[182],"result":[183],"shows":[184],"that,":[185],"both":[187],"3-gram":[188],"6-gram":[190],"showed":[194],"best":[196],"performance":[197],"in":[198],"terms":[199],"F1-score":[201],"identify":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
