{"id":"https://openalex.org/W3010661194","doi":"https://doi.org/10.1109/tifs.2020.2980190","title":"<i>CPA</i>: Accurate <i>C</i>ross-<i>P</i>latform Binary <i>A</i>uthorship Characterization Using LDA","display_name":"<i>CPA</i>: Accurate <i>C</i>ross-<i>P</i>latform Binary <i>A</i>uthorship Characterization Using LDA","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3010661194","doi":"https://doi.org/10.1109/tifs.2020.2980190","mag":"3010661194"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2020.2980190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2020.2980190","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Information Forensics and Security","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/A5000085565","display_name":"Saed Alrabaee","orcid":"https://orcid.org/0000-0001-8842-493X"},"institutions":[{"id":"https://openalex.org/I201726411","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862","country_code":"AE","type":"education","lineage":["https://openalex.org/I201726411"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Saed Alrabaee","raw_affiliation_strings":["Information Systems and Security Department, United Arab Emirates University, Al Ain, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-8842-493X","affiliations":[{"raw_affiliation_string":"Information Systems and Security Department, United Arab Emirates University, Al Ain, United Arab Emirates","institution_ids":["https://openalex.org/I201726411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028605138","display_name":"Mourad Debbabi","orcid":"https://orcid.org/0000-0003-3015-3043"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mourad Debbabi","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730397","display_name":"Lingyu Wang","orcid":"https://orcid.org/0000-0002-7441-7541"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lingyu Wang","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7441-7541","affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1769,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90184834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"3051","last_page":"3066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7743107080459595},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6230396032333374},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.5852351784706116},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5626423954963684},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5325967669487},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5310271978378296},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48386967182159424},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.45590725541114807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.450689435005188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40512993931770325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3661394715309143},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.35625022649765015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31459587812423706},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2064596712589264},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.13783398270606995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743107080459595},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6230396032333374},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.5852351784706116},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5626423954963684},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5325967669487},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5310271978378296},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48386967182159424},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.45590725541114807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450689435005188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40512993931770325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3661394715309143},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35625022649765015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31459587812423706},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2064596712589264},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.13783398270606995},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2020.2980190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2020.2980190","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5327211872","display_name":null,"funder_award_id":"G00003261","funder_id":"https://openalex.org/F4320323593","funder_display_name":"United Arab Emirates University"}],"funders":[{"id":"https://openalex.org/F4320323593","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W54929040","https://openalex.org/W165726963","https://openalex.org/W1463623766","https://openalex.org/W1580559113","https://openalex.org/W1673310716","https://openalex.org/W1779974843","https://openalex.org/W1880262756","https://openalex.org/W1910686388","https://openalex.org/W2006685053","https://openalex.org/W2023536175","https://openalex.org/W2082594235","https://openalex.org/W2085416455","https://openalex.org/W2092942461","https://openalex.org/W2098262260","https://openalex.org/W2110792853","https://openalex.org/W2129364433","https://openalex.org/W2148606255","https://openalex.org/W2182191857","https://openalex.org/W2205815960","https://openalex.org/W2514974017","https://openalex.org/W2518895230","https://openalex.org/W2562255476","https://openalex.org/W2564822508","https://openalex.org/W2582361049","https://openalex.org/W2742948365","https://openalex.org/W2749008552","https://openalex.org/W2750788884","https://openalex.org/W2774286308","https://openalex.org/W2795235421","https://openalex.org/W2882319491","https://openalex.org/W2886161275","https://openalex.org/W2920627032","https://openalex.org/W2926178846","https://openalex.org/W2941288924","https://openalex.org/W2963846926","https://openalex.org/W3105926539","https://openalex.org/W4247464060","https://openalex.org/W6602179964","https://openalex.org/W6634623742","https://openalex.org/W6637131181","https://openalex.org/W6639619044","https://openalex.org/W6639864006","https://openalex.org/W6687750345","https://openalex.org/W6731243579"],"related_works":["https://openalex.org/W2134880816","https://openalex.org/W2111298487","https://openalex.org/W4308157887","https://openalex.org/W1996787397","https://openalex.org/W2055498716","https://openalex.org/W2014463444","https://openalex.org/W2279238589","https://openalex.org/W2510680828","https://openalex.org/W4386075138","https://openalex.org/W1984130439"],"abstract_inverted_index":{"Binary":[0],"authorship":[1],"characterization":[2],"refers":[3],"to":[4,14,25,38,104,109,180,219],"the":[5,15,27,39,53,98,159,167,176,201,208,221],"process":[6],"of":[7,17,34,41,55,59,70,76,79,145,161,203,210],"identifying":[8],"stylistic":[9],"characteristics":[10,115],"that":[11],"are":[12],"related":[13,37],"author":[16,80,83,90,106,113],"an":[18],"anonymous":[19],"binary":[20,42],"code.":[21,43],"The":[22],"aim":[23],"is":[24],"automate":[26],"laborious":[28],"and":[29,89,133,138],"error-prone":[30],"reverse":[31],"engineering":[32],"task":[33],"discovering":[35],"information":[36],"author(s)":[40],"This":[44],"paper":[45],"presents":[46],"CPA,":[47],"a":[48,68,142,148,224],"novel":[49],"approach":[50],"for":[51],"characterizing":[52],"authors":[54,146,162,222],"program":[56],"binaries.":[57,118],"Instead":[58],"using":[60,189],"generic":[61],"features":[62,72],"such":[63],"as":[64],"n-grams,":[65],"CPA":[66,121,216],"proposes":[67],"set":[69],"new":[71],"based":[73],"on":[74,122],"collections":[75],"various":[77],"aspects":[78],"style,":[81],"including":[82],"code":[84,86,177,184,211],"traits,":[85],"structure":[87],"characteristics,":[88],"expertise":[91],"in":[92,116,131,198,207],"solving":[93],"coding":[94],"tasks.":[95],"It":[96],"employs":[97],"Latent":[99],"Dirichlet":[100],"Allocation":[101],"(LDA)":[102],"algorithm":[103],"generate":[105],"style":[107,114],"signatures":[108],"help":[110],"identify":[111,220],"similar":[112],"other":[117],"We":[119],"evaluated":[120],"large":[123,143],"datasets":[124],"extracted":[125],"from":[126],"selected":[127],"opensource":[128],"C/C++":[129],"projects":[130],"GitHub":[132],"Google":[134],"Code":[135],"Jam":[136],"events,":[137],"it":[139],"successfully":[140],"attributed":[141],"number":[144,160],"with":[147,223],"significantly":[149],"higher":[150],"F":[151,226],"<sub":[152,227],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153,228],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[154,229],"score:":[155],"around":[156,173,231],"91%":[157],"when":[158],"was":[163,171,178,187,194,217],"1,500.":[164],"In":[165],"addition,":[166],"false":[168],"positive":[169],"rate":[170],"low,":[172],"1.5%.":[174],"When":[175],"subjected":[179],"refactoring":[181],"techniques":[182],"or":[183,186],"transformation":[185],"processed":[188],"different":[190],"compilers/compilation":[191],"settings,":[192],"there":[193],"no":[195],"significant":[196],"drop":[197],"accuracy,":[199],"demonstrating":[200],"robustness":[202],"our":[204],"tool.":[205],"Finally,":[206],"case":[209],"written":[212],"by":[213],"multiple":[214],"authors,":[215],"able":[218],"high":[225],"score,":[230],"89%.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}