{"id":"https://openalex.org/W2766353929","doi":"https://doi.org/10.1145/3128572.3140446","title":"Malware Classification and Class Imbalance via Stochastic Hashed LZJD","display_name":"Malware Classification and Class Imbalance via Stochastic Hashed LZJD","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2766353929","doi":"https://doi.org/10.1145/3128572.3140446","mag":"2766353929"},"language":"en","primary_location":{"id":"doi:10.1145/3128572.3140446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3128572.3140446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security","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/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I4210113003","display_name":"Physical Sciences (United States)","ror":"https://ror.org/021qvjc46","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113003"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Laboratory For Physical Sciences, Catonsville, MD, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory For Physical Sciences, Catonsville, MD, USA","institution_ids":["https://openalex.org/I4210113003"]}]},{"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/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["University of Maryland, Baltimore County, Catonsville, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Catonsville, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068036546"],"corresponding_institution_ids":["https://openalex.org/I4210113003"],"apc_list":null,"apc_paid":null,"fwci":5.4061,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96676881,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"120"},"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":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8406317830085754},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7434616684913635},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7172763347625732},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6023750305175781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5849233269691467},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5843188762664795},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5801011919975281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492343306541443},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5272834897041321},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4800373315811157},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.4724465012550354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4692036509513855},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46172896027565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43989938497543335},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3223474621772766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2696417570114136},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09101417660713196},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08588895201683044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406317830085754},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7434616684913635},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7172763347625732},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6023750305175781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5849233269691467},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5843188762664795},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5801011919975281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492343306541443},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5272834897041321},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4800373315811157},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.4724465012550354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4692036509513855},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46172896027565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43989938497543335},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3223474621772766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2696417570114136},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09101417660713196},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08588895201683044},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3128572.3140446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3128572.3140446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W107173025","https://openalex.org/W1575078351","https://openalex.org/W1576442155","https://openalex.org/W1982402725","https://openalex.org/W1987684126","https://openalex.org/W1996646428","https://openalex.org/W1999092742","https://openalex.org/W2004511978","https://openalex.org/W2018175892","https://openalex.org/W2070996757","https://openalex.org/W2083183119","https://openalex.org/W2101807845","https://openalex.org/W2102221597","https://openalex.org/W2107745473","https://openalex.org/W2121749752","https://openalex.org/W2122672392","https://openalex.org/W2122962290","https://openalex.org/W2126907894","https://openalex.org/W2129650357","https://openalex.org/W2132069633","https://openalex.org/W2132791018","https://openalex.org/W2138644293","https://openalex.org/W2144112223","https://openalex.org/W2144221002","https://openalex.org/W2148143831","https://openalex.org/W2154223969","https://openalex.org/W2155615465","https://openalex.org/W2155653793","https://openalex.org/W2170529403","https://openalex.org/W2172607710","https://openalex.org/W2203388234","https://openalex.org/W2220253305","https://openalex.org/W2518866423","https://openalex.org/W2521200999","https://openalex.org/W2534043454","https://openalex.org/W2590294838","https://openalex.org/W2604248105","https://openalex.org/W2608296545","https://openalex.org/W2742475488","https://openalex.org/W2770490030","https://openalex.org/W2788864200","https://openalex.org/W4234423918","https://openalex.org/W4293713156"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W2913569734","https://openalex.org/W3127229356","https://openalex.org/W2000801317","https://openalex.org/W2294604808","https://openalex.org/W2749089722","https://openalex.org/W2702570413"],"abstract_inverted_index":{"There":[0],"are":[1],"currently":[2],"few":[3],"methods":[4,94],"that":[5],"can":[6,120],"be":[7,121],"applied":[8],"to":[9,18,52,78,92,106,124,133],"malware":[10],"classification":[11],"problems":[12],"which":[13,85],"don't":[14],"require":[15],"domain":[16,117,127],"knowledge":[17],"apply.":[19],"In":[20],"this":[21],"work,":[22],"we":[23],"develop":[24],"our":[25,71,109],"new":[26,72,126],"SHWeL":[27,40,73,97],"feature":[28],"vector":[29],"representation,":[30],"by":[31],"extending":[32],"the":[33,81,114],"recently":[34],"proposed":[35],"Lempel-Ziv":[36],"Jaccard":[37],"Distance.":[38],"These":[39],"vectors":[41],"improve":[42],"upon":[43],"LZJD's":[44],"accuracy,":[45],"outperform":[46],"byte":[47,62,135],"n-grams,":[48],"and":[49,64],"allow":[50],"us":[51,77],"build":[53],"efficient":[54],"algorithms":[55],"for":[56,88],"both":[57],"training":[58],"(a":[59,66],"weakness":[60,67],"of":[61,68,116],"n-grams)":[63],"inference":[65],"LZJD).":[69],"Furthermore,":[70],"method":[74],"also":[75],"allows":[76],"directly":[79],"tackle":[80],"class":[82],"imbalance":[83],"problem,":[84],"is":[86,111,130],"common":[87],"malware-related":[89],"tasks.":[90],"Compared":[91],"existing":[93],"like":[95],"SMOTE,":[96],"provides":[98],"significantly":[99],"improved":[100],"accuracy":[101],"while":[102],"reducing":[103],"algorithmic":[104],"complexity":[105],"O(N).":[107],"Because":[108],"approach":[110],"developed":[112],"without":[113],"use":[115],"knowledge,":[118],"it":[119],"easily":[122],"re-applied":[123],"any":[125],"where":[128],"there":[129],"a":[131],"need":[132],"classify":[134],"sequences.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}