{"id":"https://openalex.org/W3123951791","doi":"https://doi.org/10.1145/3457682.3457756","title":"Content-Based Textual File Type Detection at Scale","display_name":"Content-Based Textual File Type Detection at Scale","publication_year":2021,"publication_date":"2021-02-26","ids":{"openalex":"https://openalex.org/W3123951791","doi":"https://doi.org/10.1145/3457682.3457756","mag":"3123951791"},"language":"en","primary_location":{"id":"doi:10.1145/3457682.3457756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3457682.3457756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.08508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033670566","display_name":"Francesca Del Bonifro","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Del Bonifro","raw_affiliation_strings":["University of Bologna, Italy","University of Bologna. Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna. Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025039355","display_name":"Maurizio Gabbrielli","orcid":"https://orcid.org/0000-0003-0609-8662"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maurizio Gabbrielli","raw_affiliation_strings":["University of Bologna, Italy","University of Bologna. Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna. Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006129685","display_name":"Stefano Zacchiroli","orcid":"https://orcid.org/0000-0002-4576-136X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefano Zacchiroli","raw_affiliation_strings":["Universite de Paris and Inria, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Paris and Inria, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"485","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9926999807357788,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.963699996471405,"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":0.8556021451950073},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6724178194999695},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6467857360839844},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6237088441848755},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.515286922454834},{"id":"https://openalex.org/keywords/file-system-fragmentation","display_name":"File system fragmentation","score":0.46452224254608154},{"id":"https://openalex.org/keywords/computer-file","display_name":"Computer file","score":0.4473504424095154},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4464668929576874},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4400617480278015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.43579646944999695},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4354187548160553},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.4140962064266205},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3980494737625122},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3437858819961548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3320186734199524},{"id":"https://openalex.org/keywords/unix-file-types","display_name":"Unix file types","score":0.2660415470600128},{"id":"https://openalex.org/keywords/stub-file","display_name":"Stub file","score":0.17125746607780457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556021451950073},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6724178194999695},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6467857360839844},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6237088441848755},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.515286922454834},{"id":"https://openalex.org/C26656859","wikidata":"https://www.wikidata.org/wiki/Q4089244","display_name":"File system fragmentation","level":4,"score":0.46452224254608154},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.4473504424095154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4464668929576874},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4400617480278015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.43579646944999695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4354187548160553},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.4140962064266205},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3980494737625122},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3437858819961548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320186734199524},{"id":"https://openalex.org/C21729314","wikidata":"https://www.wikidata.org/wiki/Q7896858","display_name":"Unix file types","level":4,"score":0.2660415470600128},{"id":"https://openalex.org/C13674803","wikidata":"https://www.wikidata.org/wiki/Q7627301","display_name":"Stub file","level":3,"score":0.17125746607780457}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3457682.3457756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3457682.3457756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.08508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08508","pdf_url":"https://arxiv.org/pdf/2101.08508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3123951791","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2101.08508","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.08508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.08508","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.08508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08508","pdf_url":"https://arxiv.org/pdf/2101.08508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W644720917","https://openalex.org/W1522301498","https://openalex.org/W1859783391","https://openalex.org/W1981922151","https://openalex.org/W1989479444","https://openalex.org/W1993867663","https://openalex.org/W1997841190","https://openalex.org/W1998899601","https://openalex.org/W2018696645","https://openalex.org/W2021565261","https://openalex.org/W2027166822","https://openalex.org/W2032652782","https://openalex.org/W2044067411","https://openalex.org/W2065312245","https://openalex.org/W2115002964","https://openalex.org/W2120358130","https://openalex.org/W2123633968","https://openalex.org/W2398791084","https://openalex.org/W2404987555","https://openalex.org/W2470673105","https://openalex.org/W2587019100","https://openalex.org/W2602842256","https://openalex.org/W2752033492","https://openalex.org/W2759020546","https://openalex.org/W2759963882","https://openalex.org/W2890432166","https://openalex.org/W2893990175","https://openalex.org/W2913200795","https://openalex.org/W2953583529","https://openalex.org/W2963935794","https://openalex.org/W3021971982","https://openalex.org/W3034566726","https://openalex.org/W3101068774","https://openalex.org/W3105133011","https://openalex.org/W3121939465","https://openalex.org/W3209878570","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3177246419","https://openalex.org/W1479753069","https://openalex.org/W3130118190","https://openalex.org/W2574274795","https://openalex.org/W2946404812","https://openalex.org/W2919352243","https://openalex.org/W1999157933","https://openalex.org/W3138081324","https://openalex.org/W2397665901","https://openalex.org/W2027166822","https://openalex.org/W3086753732","https://openalex.org/W2783978961","https://openalex.org/W2756118627","https://openalex.org/W2964315653","https://openalex.org/W2993418011","https://openalex.org/W155778206","https://openalex.org/W1882160271","https://openalex.org/W2559784535","https://openalex.org/W3012259356","https://openalex.org/W2823578223"],"abstract_inverted_index":{"Programming":[0],"language":[1],"detection":[2],"is":[3,16,63],"a":[4,19,113,119,142,186],"common":[5],"need":[6],"in":[7,51,129,182],"the":[8,40,45,78,104,176],"analysis":[9],"of":[10,21,42,47,107,190],"large":[11],"source":[12,67,86,108],"code":[13,53,68,74,87,109],"bases.":[14],"It":[15],"supported":[17],"by":[18],"number":[20,189],"existing":[22,167],"tools":[23],"that":[24,69,88,116],"rely":[25],"on":[26,57,77,103,136],"several":[27],"features,":[28],"and":[29,98,139],"most":[30],"notably":[31],"file":[32,36,59,71,96,168,196],"extensions,":[33,97],"to":[34,65,83],"determine":[35],"types.":[37],"We":[38,111],"consider":[39],"problem":[41],"accurately":[43],"detecting":[44],"type":[46],"files":[48,156],"commonly":[49],"found":[50],"software":[52],"bases,":[54],"based":[55,135],"solely":[56],"textual":[58,124,155],"content.":[60],"Doing":[61],"so":[62],"helpful":[64],"classify":[66],"lack":[70],"extensions":[72,169],"(e.g.,":[73],"snippets":[75],"posted":[76],"Web":[79],"or":[80,94],"executable":[81],"scripts),":[82],"avoid":[84],"misclassifying":[85],"has":[89],"been":[90],"recorded":[91],"with":[92,161],"wrong":[93],"uncommon":[95],"also":[99],"shed":[100],"some":[101],"light":[102],"intrinsic":[105],"recognizability":[106],"files.":[110],"propose":[112],"simple":[114,143],"model":[115,178],"(a)":[117],"use":[118,141,154],"language-agnostic":[120],"word":[121],"tokenizer":[122],"for":[123,185],"files,":[125],"(b)":[126],"group":[127],"tokens":[128],"1-/2-grams,":[130],"(c)":[131],"build":[132],"feature":[133],"vectors":[134],"N-gram":[137],"frequencies,":[138],"(d)":[140],"fully":[144],"connected":[145],"neural":[146],"network":[147],"as":[148,170],"classifier.":[149],"As":[150],"training":[151],"set":[152],"we":[153],"extracted":[157],"from":[158],"GitHub":[159],"repositories":[160],"at":[162],"least":[163],"1000":[164],"stars,":[165],"using":[166],"ground":[171],"truth.":[172],"Despite":[173],"its":[174],"simplicity":[175],"proposed":[177],"reaches":[179],"\u2248":[180],"85%":[181],"our":[183],"experiments":[184],"relatively":[187],"high":[188],"recognized":[191],"classes":[192],"(more":[193],"than":[194],"130":[195],"types).":[197]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}