{"id":"https://openalex.org/W4382135412","doi":"https://doi.org/10.3390/info14070361","title":"Authorship Identification of Binary and Disassembled Codes Using NLP Methods","display_name":"Authorship Identification of Binary and Disassembled Codes Using NLP Methods","publication_year":2023,"publication_date":"2023-06-25","ids":{"openalex":"https://openalex.org/W4382135412","doi":"https://doi.org/10.3390/info14070361"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14070361","pdf_url":"https://www.mdpi.com/2078-2489/14/7/361/pdf?version=1687697574","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/14/7/361/pdf?version=1687697574","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047524267","display_name":"Aleksandr Romanov","orcid":"https://orcid.org/0000-0002-2587-2222"},"institutions":[{"id":"https://openalex.org/I114376631","display_name":"Tomsk State University of Control Systems and Radio-Electronics","ror":"https://ror.org/032j5hw78","country_code":"RU","type":"education","lineage":["https://openalex.org/I114376631"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksandr Romanov","raw_affiliation_strings":["Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia"],"affiliations":[{"raw_affiliation_string":"Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia","institution_ids":["https://openalex.org/I114376631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058040901","display_name":"Anna Kurtukova","orcid":"https://orcid.org/0000-0001-5619-1836"},"institutions":[{"id":"https://openalex.org/I114376631","display_name":"Tomsk State University of Control Systems and Radio-Electronics","ror":"https://ror.org/032j5hw78","country_code":"RU","type":"education","lineage":["https://openalex.org/I114376631"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Anna Kurtukova","raw_affiliation_strings":["Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia"],"affiliations":[{"raw_affiliation_string":"Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia","institution_ids":["https://openalex.org/I114376631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061176835","display_name":"Anastasia Fedotova","orcid":"https://orcid.org/0000-0001-7844-4363"},"institutions":[{"id":"https://openalex.org/I114376631","display_name":"Tomsk State University of Control Systems and Radio-Electronics","ror":"https://ror.org/032j5hw78","country_code":"RU","type":"education","lineage":["https://openalex.org/I114376631"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anastasia Fedotova","raw_affiliation_strings":["Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia"],"affiliations":[{"raw_affiliation_string":"Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia","institution_ids":["https://openalex.org/I114376631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029791948","display_name":"Alexander Shelupanov","orcid":"https://orcid.org/0000-0003-2393-6701"},"institutions":[{"id":"https://openalex.org/I114376631","display_name":"Tomsk State University of Control Systems and Radio-Electronics","ror":"https://ror.org/032j5hw78","country_code":"RU","type":"education","lineage":["https://openalex.org/I114376631"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexander Shelupanov","raw_affiliation_strings":["Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia"],"affiliations":[{"raw_affiliation_string":"Department of Security, Tomsk State University of Control Systems and Radioelectronics, 634050 Tomsk, Russia","institution_ids":["https://openalex.org/I114376631"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058040901"],"corresponding_institution_ids":["https://openalex.org/I114376631"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515,"provenance":"doaj"},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515,"provenance":"doaj"},"fwci":0.352,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.606989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":68,"max":79},"biblio":{"volume":"14","issue":"7","first_page":"361","last_page":"361"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9974,"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":0.9974,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9952,"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/T10260","display_name":"Software Engineering Research","score":0.9919,"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/executable","display_name":"Executable","score":0.8501773},{"id":"https://openalex.org/keywords/identification","display_name":"Identification","score":0.73232234},{"id":"https://openalex.org/keywords/reverse-engineering","display_name":"Reverse engineering","score":0.63654},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5369534},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.43878096}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8501773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185655},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.73232234},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7020284},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6820865},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.63654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602649},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5535439},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5369534},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4817855},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48077387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45579514},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.43878096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3989657},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2671314},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08855909},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.066899866},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14070361","pdf_url":"https://www.mdpi.com/2078-2489/14/7/361/pdf?version=1687697574","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14070361","pdf_url":"https://www.mdpi.com/2078-2489/14/7/361/pdf?version=1687697574","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W2129364433","https://openalex.org/W2503713833","https://openalex.org/W2516577067","https://openalex.org/W2611488578","https://openalex.org/W2891865791","https://openalex.org/W2941288924","https://openalex.org/W2952107551","https://openalex.org/W2976414818","https://openalex.org/W3101243405","https://openalex.org/W3110868551","https://openalex.org/W3194447707","https://openalex.org/W4226181420","https://openalex.org/W4229030202","https://openalex.org/W4303645051","https://openalex.org/W4319072600"],"related_works":["https://openalex.org/W4240624848","https://openalex.org/W4210907385","https://openalex.org/W3120610872","https://openalex.org/W2598672065","https://openalex.org/W2523911541","https://openalex.org/W2132081528","https://openalex.org/W2112192942","https://openalex.org/W1995118279","https://openalex.org/W1993817217","https://openalex.org/W1638297612"],"abstract_inverted_index":{"This":[0],"article":[1],"is":[2,18,36],"part":[3],"of":[4,12,22,65,92,127,152,168],"a":[5,19,90],"series":[6],"aimed":[7],"at":[8],"determining":[9],"the":[10,72,134,140,145,166,169],"authorship":[11,49],"source":[13,93,110,146],"codes.":[14],"Analyzing":[15],"binary":[16],"code":[17],"crucial":[20],"aspect":[21],"cybersecurity,":[23],"software":[24],"development,":[25],"and":[26,46,71,98,104,117,157,172],"computer":[27],"forensics,":[28],"particularly":[29],"in":[30,78,81,96,154,160],"identifying":[31],"malware":[32],"authors.":[33],"Any":[34],"program":[35],"machine":[37,69],"code,":[38],"which":[39],"can":[40],"be":[41],"disassembled":[42,119,131],"using":[43,56,89,120,133],"specialized":[44],"tools":[45],"analyzed":[47],"for":[48,130],"identification,":[50],"similar":[51],"to":[52,175],"natural":[53],"language":[54],"text":[55],"Natural":[57],"Language":[58],"Processing":[59],"methods.":[60],"We":[61],"propose":[62],"an":[63,149],"ensemble":[64],"fastText,":[66],"support":[67],"vector":[68],"(SVM),":[70],"authors\u2019":[73],"hybrid":[74],"neural":[75],"network":[76],"developed":[77,170],"previous":[79],"works":[80],"this":[82],"research.":[83],"The":[84,108,124],"improved":[85,135],"methodology":[86,136,141,171],"was":[87,142],"evaluated":[88],"dataset":[91],"codes":[94,111,132],"written":[95],"C":[97],"C++":[99],"languages":[100],"collected":[101,109],"from":[102],"GitHub":[103],"Google":[105],"Code":[106],"Jam.":[107],"were":[112],"compiled":[113],"into":[114],"executable":[115],"programs":[116],"then":[118],"reverse":[121],"engineering":[122],"tools.":[123],"average":[125,150],"accuracy":[126,151],"author":[128],"identification":[129],"exceeds":[137],"0.90.":[138],"Additionally,":[139],"tested":[143],"on":[144],"codes,":[147],"achieving":[148],"0.96":[153],"simple":[155],"cases":[156],"over":[158],"0.85":[159],"complex":[161],"cases.":[162],"These":[163],"results":[164],"validate":[165],"effectiveness":[167],"its":[173],"applicability":[174],"solving":[176],"cybersecurity":[177],"challenges.":[178]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4382135412","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2024-12-21T15:48:02.910074","created_date":"2023-06-27"}