{"id":"https://openalex.org/W1529790664","doi":null,"title":"Identifying Authorship by Byte-Level N-Grams: The Source Code Author Profile (SCAP) Method.","display_name":"Identifying Authorship by Byte-Level N-Grams: The Source Code Author Profile (SCAP) Method.","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1529790664","mag":"1529790664"},"language":"en","primary_location":{"id":"mag:1529790664","doi":null,"is_oa":false,"landing_page_url":"https://www.utica.edu/academic/institutes/ecii/publications/articles/B41158D1-C829-0387-009D214D2170C321.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S137137093","display_name":"International journal of digital evidence","issn_l":"1938-0917","issn":["1938-0917"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International journal of digital evidence","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5057577851","display_name":"Georgia Frantzeskou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgia Frantzeskou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061737423","display_name":"Efstathios Stamatatos","orcid":"https://orcid.org/0000-0002-1336-9128","observed_orcids":["https://orcid.org/0000-0002-1336-9128"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Efstathios Stamatatos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1336-9128","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091815745","display_name":"Stefanos Gritzalis","orcid":"https://orcid.org/0000-0002-8037-2191","observed_orcids":["https://orcid.org/0000-0002-8037-2191"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefanos Gritzalis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8037-2191","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014954474","display_name":"Carole E. Chaski","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carole E. Chaski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086984307","display_name":"Blake Stephen Howald","orcid":"https://orcid.org/0009-0001-3482-6957","observed_orcids":["https://orcid.org/0009-0001-3482-6957"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Blake Stephen Howald","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-3482-6957","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4321,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.84280553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9735999703407288,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9735999703407288,"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":0.02070000022649765,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.0007999999797903001,"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/author-profiling","display_name":"author profiling","score":0.5249999761581421},{"id":"https://openalex.org/keywords/programming-style","display_name":"programming style","score":0.4519999921321869},{"id":"https://openalex.org/keywords/digital-forensics","display_name":"digital forensics","score":0.828000009059906},{"id":"https://openalex.org/keywords/cybercrime-investigation","display_name":"cybercrime investigation","score":0.5239999890327454},{"id":"https://openalex.org/keywords/intellectual-property-infringement","display_name":"intellectual property infringement","score":0.8389999866485596},{"id":"https://openalex.org/keywords/similarity-measures","display_name":"similarity measures","score":0.47200000286102295},{"id":"https://openalex.org/keywords/programming-language-independence","display_name":"programming language independence","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538236618041992},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.710552990436554},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6944016218185425},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5539752244949341},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5375928282737732},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5301101207733154},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.44505229592323303},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.42723917961120605},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4038611948490143},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35463473200798035},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:1529790664","doi":null,"is_oa":false,"landing_page_url":"https://www.utica.edu/academic/institutes/ecii/publications/articles/B41158D1-C829-0387-009D214D2170C321.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S137137093","display_name":"International journal of digital evidence","issn_l":"1938-0917","issn":["1938-0917"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International journal of digital evidence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W72037277","https://openalex.org/W1540672006","https://openalex.org/W1574086225","https://openalex.org/W1978223246","https://openalex.org/W2010452235","https://openalex.org/W2044555705","https://openalex.org/W2054944591","https://openalex.org/W2072164438","https://openalex.org/W2083798989","https://openalex.org/W2097278375","https://openalex.org/W2127324866","https://openalex.org/W2128305971","https://openalex.org/W2144270983","https://openalex.org/W2151752770","https://openalex.org/W2180101149"],"related_works":["https://openalex.org/W7095655413","https://openalex.org/W7096446095","https://openalex.org/W1956188504","https://openalex.org/W2054126054","https://openalex.org/W7099722291","https://openalex.org/W2163823069","https://openalex.org/W1540672006","https://openalex.org/W8260271","https://openalex.org/W2122219434","https://openalex.org/W2082439824"],"abstract_inverted_index":{"Source":[0,231],"code":[1,41,51,104,133,163,275,290],"author":[2,10,20,81,247],"identification":[3,66],"deals":[4,180],"with":[5,183],"identifying":[6],"the":[7,48,54,68,79,89,102,129,165,177,211,216,246,262,283,316],"most":[8],"likely":[9],"of":[11,18,29,50,131,155,167,190,213,230,238,248,253,264,285,315,319],"a":[12,16,33,57,85,111,139,143,187,219,235,249,292,297,312],"computer":[13],"program,":[14],"given":[15],"set":[17],"predefined":[19,80],"candidates.":[21,82],"There":[22],"are":[23],"several":[24],"scenarios":[25],"where":[26,185],"digital":[27,301],"evidence":[28],"this":[30],"kind":[31],"plays":[32],"role":[34],"in":[35,53,64,210,215,223,234,261,291],"investigation":[36],"and":[37,60,142,161,271,278,304],"adjudication,":[38],"such":[39],"as":[40],"authorship":[42,119,276,284],"disputes,":[43,277],"intellectual":[44,279],"property":[45,280],"infringement,":[46],"tracing":[47],"source":[49,103,132,217,289,320],"left":[52],"system":[55],"after":[56],"cyber":[58,259],"attack,":[59],"so":[61],"forth.":[62],"As":[63],"any":[65],"task,":[67],"disputed":[69],"program":[70],"is":[71,173,196,202,242],"compared":[72],"to":[73,115,244],"undisputed,":[74],"known":[75],"programming":[76,254],"samples":[77],"by":[78],"We":[83],"present":[84],"new":[86],"approach,":[87,95],"called":[88],"SCAP":[90,108,171,178,206],"(Source":[91],"Code":[92,232],"Author":[93],"Profiles)":[94],"based":[96],"on":[97,152],"byte-level":[98],"n-gram":[99,125],"profiles":[100],"representing":[101],"author\u2019s":[105],"style.":[106],"The":[107,135,170,227],"method":[109,112],"extends":[110],"originally":[113],"applied":[114],"natural":[116],"language":[117],"text":[118],"attribution;":[120],"we":[121],"show":[122],"that":[123,205],"an":[124],"approach":[126,172,179],"also":[127,203],"suits":[128],"characteristics":[130],"analysis.":[134],"methodological":[136],"extension":[137],"includes":[138],"simplified":[140],"profile":[141],"less":[144],"complicated,":[145],"but":[146],"more":[147],"effective,":[148],"similarity":[149],"measure.":[150],"Experiments":[151],"data":[153],"sets":[154],"different":[156],"programming-language":[157,174],"(Java":[158],"or":[159,287],"C++)":[160],"commented/commentless":[162],"demonstrate":[164],"effectiveness":[166,207],"these":[168],"extensions.":[169],"independent.":[175],"Moreover,":[176],"surprisingly":[181],"well":[182],"cases":[184,240],"only":[186],"limited":[188,251],"amount":[189],"very":[191],"short":[192],"programs":[193],"per":[194],"programmer":[195],"available":[197],"for":[198,300,311],"training.":[199],"Finally,":[200],"it":[201,241],"demonstrated":[204],"persists":[208],"even":[209],"absence":[212],"comments":[214],"code,":[218],"condition":[220],"usually":[221,250],"met":[222],"cyber-crime":[224],"cases.":[225],"1.":[226],"Forensic":[228],"Significance":[229],"Nowadays,":[233],"wide":[236],"variety":[237],"legal":[239,313],"important":[243],"identify":[245],"piece":[252],"code.":[255,321],"Such":[256],"situations":[257],"include":[258],"attacks":[260],"form":[263],"viruses,":[265],"Trojan":[266],"horses,":[267],"logic":[268],"bombs,":[269],"fraud,":[270],"credit":[272],"card":[273],"cloning,":[274],"infringement.":[281],"Identifying":[282],"malicious":[286],"stolen":[288],"reliable":[293],"way":[294],"has":[295],"become":[296],"primary":[298],"goal":[299],"investigators":[302],"(Spafford":[303],"Weeber":[305],"1993).":[306],"Please":[307],"see":[308],"Appendix":[309],"1":[310],"analysis":[314],"forensic":[317],"significance":[318]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":10}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}