{"id":"https://openalex.org/W2792663539","doi":"https://doi.org/10.1109/malware.2017.8323963","title":"What can N-grams learn for malware detection?","display_name":"What can N-grams learn for malware detection?","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2792663539","doi":"https://doi.org/10.1109/malware.2017.8323963","mag":"2792663539"},"language":"en","primary_location":{"id":"doi:10.1109/malware.2017.8323963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2017.8323963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference on Malicious and Unwanted Software (MALWARE)","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/A5048807150","display_name":"Richard Zak","orcid":"https://orcid.org/0000-0003-4272-2565"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Zak","raw_affiliation_strings":["Laboratory for Physical Sciences Booz Allen Hamilton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences Booz Allen Hamilton","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Laboratory for Physical Sciences Booz Allen Hamilton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences Booz Allen Hamilton","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025012064","display_name":"Charles Nicholas","orcid":"https://orcid.org/0000-0001-9494-7139"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["University of Maryland, Baltimore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore","institution_ids":["https://openalex.org/I126744593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1748,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93107684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9943000078201294,"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/T10260","display_name":"Software Engineering Research","score":0.9898999929428101,"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/byte","display_name":"Byte","score":0.9038881063461304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308315277099609},{"id":"https://openalex.org/keywords/opcode","display_name":"Opcode","score":0.787753164768219},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7667350172996521},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5482922792434692},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5147318840026855},{"id":"https://openalex.org/keywords/malware-analysis","display_name":"Malware analysis","score":0.506152331829071},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44556817412376404},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4376699924468994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.383367121219635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3209832012653351},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27591651678085327},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2412230670452118},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16708868741989136},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.15409418940544128},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0990033745765686}],"concepts":[{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.9038881063461304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308315277099609},{"id":"https://openalex.org/C52173422","wikidata":"https://www.wikidata.org/wiki/Q766483","display_name":"Opcode","level":2,"score":0.787753164768219},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7667350172996521},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5482922792434692},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5147318840026855},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.506152331829071},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44556817412376404},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4376699924468994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.383367121219635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3209832012653351},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27591651678085327},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2412230670452118},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16708868741989136},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.15409418940544128},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0990033745765686},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/malware.2017.8323963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2017.8323963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference on Malicious and Unwanted Software (MALWARE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W36091977","https://openalex.org/W135165129","https://openalex.org/W152196245","https://openalex.org/W646354405","https://openalex.org/W1482612322","https://openalex.org/W1548500763","https://openalex.org/W1564075167","https://openalex.org/W1567046609","https://openalex.org/W1760401052","https://openalex.org/W1893133781","https://openalex.org/W1966948031","https://openalex.org/W1973211701","https://openalex.org/W2003094813","https://openalex.org/W2004915807","https://openalex.org/W2006546769","https://openalex.org/W2011224223","https://openalex.org/W2034938003","https://openalex.org/W2042742130","https://openalex.org/W2044660163","https://openalex.org/W2075917870","https://openalex.org/W2083183119","https://openalex.org/W2101807845","https://openalex.org/W2104912713","https://openalex.org/W2120100126","https://openalex.org/W2121749752","https://openalex.org/W2122825543","https://openalex.org/W2141577524","https://openalex.org/W2144112223","https://openalex.org/W2146567535","https://openalex.org/W2150188172","https://openalex.org/W2154529672","https://openalex.org/W2155653793","https://openalex.org/W2165357553","https://openalex.org/W2165966284","https://openalex.org/W2166462894","https://openalex.org/W2170529403","https://openalex.org/W2170770919","https://openalex.org/W2203388234","https://openalex.org/W2215444025","https://openalex.org/W2281824022","https://openalex.org/W2484332939","https://openalex.org/W2518866423","https://openalex.org/W2608296545","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W3103457769","https://openalex.org/W4212883601","https://openalex.org/W6601441165","https://openalex.org/W6606250027","https://openalex.org/W6621201870","https://openalex.org/W6632780167","https://openalex.org/W6633665954","https://openalex.org/W6634033044","https://openalex.org/W6637891688","https://openalex.org/W6675913052","https://openalex.org/W6677770173","https://openalex.org/W6678051712","https://openalex.org/W6684832316","https://openalex.org/W6688455154","https://openalex.org/W6695559068","https://openalex.org/W6726771526","https://openalex.org/W6736941266"],"related_works":["https://openalex.org/W36091977","https://openalex.org/W2800331776","https://openalex.org/W4382794599","https://openalex.org/W2903602818","https://openalex.org/W2003791967","https://openalex.org/W4294976063","https://openalex.org/W4387382577","https://openalex.org/W3016048014","https://openalex.org/W2902612505","https://openalex.org/W2384735743"],"abstract_inverted_index":{"Recent":[0],"work":[1,44],"has":[2,19],"shown":[3],"that":[4,40,96,116,128],"byte":[5,24,47,97],"n-grams":[6,25,98,118],"learn":[7,27,100,109],"mostly":[8],"low":[9],"entropy":[10,32],"features,":[11],"such":[12,34],"as":[13,35,122,124],"function":[14],"imports":[15],"and":[16,58,83,127],"strings,":[17],"which":[18],"brought":[20],"into":[21],"question":[22],"whether":[23],"can":[26,99],"information":[28],"corresponding":[29],"to":[30,60,85],"higher":[31],"levels,":[33],"binary":[36,56,133],"code.":[37],"We":[38,73,113],"investigate":[39],"hypothesis":[41],"in":[42,80],"this":[43,75],"by":[45,63,76,131],"performing":[46],"n-gram":[48,64],"analysis":[49,65],"on":[50,66],"only":[51],"specific":[52],"sub-sections":[53],"of":[54],"the":[55,78,89,102],"file,":[57],"compare":[59],"results":[61],"obtained":[62],"assembly":[67,117],"code":[68,103],"generated":[69],"from":[70,101],"disassembled":[71],"binaries.":[72],"do":[74,106],"leveraging":[77],"change":[79],"model":[81,146],"performance":[82],"ensembles":[84],"glean":[86],"insights":[87],"about":[88],"data.":[90],"In":[91],"doing":[92],"so":[93],"we":[94],"discover":[95,115],"regions,":[104],"but":[105],"not":[107,120,137],"necessarily":[108],"any":[110],"new":[111],"information.":[112],"also":[114],"may":[119],"be":[121],"effective":[123],"previously":[125,138],"thought":[126],"disambiguating":[129],"instructions":[130],"their":[132],"opcode,":[134],"an":[135],"approach":[136],"used":[139],"for":[140,145],"malware":[141],"detection,":[142],"is":[143],"critical":[144],"generalization.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}