{"id":"https://openalex.org/W2042058229","doi":"https://doi.org/10.1145/1599272.1599278","title":"Malware detection using statistical analysis of byte-level file content","display_name":"Malware detection using statistical analysis of byte-level file content","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2042058229","doi":"https://doi.org/10.1145/1599272.1599278","mag":"2042058229"},"language":"en","primary_location":{"id":"doi:10.1145/1599272.1599278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1599272.1599278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGKDD Workshop on CyberSecurity and Intelligence Informatics","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/A5077609157","display_name":"S. Momina Tabish","orcid":null},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"S. Momina Tabish","raw_affiliation_strings":["National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#"],"affiliations":[{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771200","display_name":"Muhammad Shafiq","orcid":"https://orcid.org/0000-0003-1909-9373"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"M. Zubair Shafiq","raw_affiliation_strings":["National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#"],"affiliations":[{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103408949","display_name":"Muddassar Farooq","orcid":"https://orcid.org/0009-0009-1882-7819"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muddassar Farooq","raw_affiliation_strings":["National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#"],"affiliations":[{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer & Emerging Sciences (FAST-NUCES), Islamabad, Pakistan#TAB#","institution_ids":["https://openalex.org/I201384688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077609157"],"corresponding_institution_ids":["https://openalex.org/I201384688"],"apc_list":null,"apc_paid":null,"fwci":4.2816,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.94164069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/byte","display_name":"Byte","score":0.8270195722579956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8153412342071533},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7062277793884277},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5086277723312378},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4711507558822632},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4363754987716675},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18697360157966614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07963237166404724}],"concepts":[{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.8270195722579956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153412342071533},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7062277793884277},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5086277723312378},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4711507558822632},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4363754987716675},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18697360157966614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07963237166404724},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1599272.1599278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1599272.1599278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGKDD Workshop on CyberSecurity and Intelligence Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.466.5074","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.466.5074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://download.adamas.ai/dlbase/ebooks/VX_related/Malware Detection using Statistical Analysis of Byte-Level File Content.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W97539848","https://openalex.org/W101893524","https://openalex.org/W1504694836","https://openalex.org/W1521843029","https://openalex.org/W1565379513","https://openalex.org/W1570448133","https://openalex.org/W1571989395","https://openalex.org/W1591966580","https://openalex.org/W1774267715","https://openalex.org/W1988790447","https://openalex.org/W1996785213","https://openalex.org/W2021308105","https://openalex.org/W2082729696","https://openalex.org/W2099053789","https://openalex.org/W2099111195","https://openalex.org/W2111216264","https://openalex.org/W2125055259","https://openalex.org/W2130728435","https://openalex.org/W2144112223","https://openalex.org/W2147169507","https://openalex.org/W2151300580","https://openalex.org/W2167671111","https://openalex.org/W2170529403","https://openalex.org/W2203388234","https://openalex.org/W2626914210","https://openalex.org/W2966207845","https://openalex.org/W4299301436","https://openalex.org/W6603957951","https://openalex.org/W6678449394","https://openalex.org/W6679033275","https://openalex.org/W6687924309"],"related_works":["https://openalex.org/W2562617734","https://openalex.org/W1827256152","https://openalex.org/W3016595359","https://openalex.org/W4379053857","https://openalex.org/W4205985752","https://openalex.org/W2738219410","https://openalex.org/W2980605179","https://openalex.org/W3045684292","https://openalex.org/W4313314976","https://openalex.org/W2167921885"],"abstract_inverted_index":{"Commercial":[0],"anti-virus":[1],"software":[2],"are":[3],"unable":[4],"to":[5,72,93,105,129],"provide":[6],"pro-tection":[7],"against":[8],"newly":[9],"launched":[10],"(a.k.a":[11],"\u201czero-day\u201d)":[12],"malware.":[13,78,135],"In":[14],"this":[15],"paper,":[16],"we":[17,119],"propose":[18],"a":[19,81,90,126,152,165,182,202],"novel":[20],"malware":[21,183,189,209],"detection":[22,210,234],"tech-nique":[23],"which":[24],"is":[25,46,64],"based":[26,43,66,208,222],"on":[27],"the":[28,58,70,95,107,121,137,142,156,219,225],"analysis":[29],"of":[30,36,84,110,125,169,186,214],"byte-level":[31,96,143],"file":[32,60,97,108,128,144],"con-tent.":[33],"The":[34,212],"novelty":[35],"our":[37,161,215],"approach,":[38],"compared":[39],"with":[40,204],"existing":[41,205,226],"content":[42,109],"mining":[44,103,207],"schemes,":[45],"that":[47,218],"it":[48,131,147],"does":[49,148],"not":[50,149],"memo-rize":[51],"specific":[52],"byte-sequences":[53],"or":[54,115,134],"strings":[55],"appearing":[56],"in":[57,89],"ac-tual":[59],"content.":[61,98],"Our":[62],"technique":[63,163,223],"non-signature":[65,221],"and":[67,76,86,179,181,197,228],"therefore":[68],"has":[69],"potential":[71],"detect":[73],"previously":[74],"unknown":[75],"zero-day":[77],"We":[79,99,158,199],"compute":[80],"wide":[82],"range":[83],"statistical":[85],"information-theoretic":[87],"features":[88],"block-wise":[91,122],"manner":[92],"quantify":[94],"leverage":[100],"standard":[101],"data":[102,206],"algorithms":[104],"classify":[106],"every":[111],"block":[112],"as":[113,132],"normal":[114],"potentially":[116],"malicious.":[117],"Finally,":[118],"corre-late":[120],"classification":[123],"results":[124,213],"given":[127],"cat-egorize":[130],"benign":[133,166],"Since":[136],"proposed":[138,162,220],"scheme":[139],"operates":[140],"at":[141],"content;":[145],"therefore,":[146],"require":[150],"any":[151],"priori":[153],"information":[154],"about":[155],"filetype.":[157],"have":[159],"tested":[160],"using":[164],"dataset":[167,184],"com-prising":[168],"six":[170,187],"different":[171,188],"filetypes":[172],"\u2014":[173,191],"DOC,":[174],"EXE,":[175],"JPG,":[176],"MP3,":[177],"PDF":[178],"ZIP":[180],"comprising":[185],"types":[190],"backdoor,":[192],"trojan,":[193],"virus,":[194],"worm,":[195],"construc-tor":[196],"miscellaneous.":[198],"also":[200],"perform":[201],"comparison":[203],"techniques.":[211],"experiments":[216],"show":[217],"surpasses":[224],"techniques":[227],"achieves":[229],"more":[230],"than":[231],"90":[232],"%":[233],"accuracy.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}