{"id":"https://openalex.org/W7225143328","doi":"https://doi.org/10.20944/preprints202611.0077.v1","title":"Revisiting Opcode Representations for Malware Family Classification: Learned Embeddings Versus Frequency Baselines","display_name":"Revisiting Opcode Representations for Malware Family Classification: Learned Embeddings Versus Frequency Baselines","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225143328","doi":"https://doi.org/10.20944/preprints202611.0077.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0077.v1","doi":"https://doi.org/10.20944/preprints202611.0077.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0077.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0077.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150454872","display_name":"Kiana Bakrani Balani","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiana Bakrani Balani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160487440","display_name":"Mohammed Nassar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Nassar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074325073","display_name":"Fabio Di Troia","orcid":"https://orcid.org/0000-0003-2355-7146","observed_orcids":["https://orcid.org/0000-0003-2355-7146"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fabio Di Troia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5074325073"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/1712","display_name":"Software"},"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/1712","display_name":"Software"},"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":0.0,"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/T11424","display_name":"Security and Verification in Computing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/malware-family-classification","display_name":"malware family classification","score":0.875},{"id":"https://openalex.org/keywords/learned-embeddings","display_name":"learned embeddings","score":0.8330000042915344},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2Vec","score":0.9580000042915344},{"id":"https://openalex.org/keywords/gloves","display_name":"gloves","score":1.0},{"id":"https://openalex.org/keywords/fasttext","display_name":"FastText","score":0.9990000128746033},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.49799999594688416},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.7490000128746033},{"id":"https://openalex.org/keywords/oversampling","display_name":"oversampling","score":0.7289999723434448},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.5659999847412109},{"id":"https://openalex.org/keywords/malware-detection","display_name":"malware detection","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C52173422","wikidata":"https://www.wikidata.org/wiki/Q766483","display_name":"Opcode","level":2,"score":0.8838000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521000027656555},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4596000015735626},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4300000071525574},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0077.v1","doi":"https://doi.org/10.20944/preprints202611.0077.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0077.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0077.v1","doi":"https://doi.org/10.20944/preprints202611.0077.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0077.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3135906542","https://openalex.org/W4243250480","https://openalex.org/W4241850557","https://openalex.org/W3117885448","https://openalex.org/W7207609116","https://openalex.org/W4224305508","https://openalex.org/W4404426922","https://openalex.org/W2955992195","https://openalex.org/W1590834663","https://openalex.org/W3201129094"],"abstract_inverted_index":{"Opcode":[0],"representations":[1,135],"provide":[2],"numerical":[3],"features":[4],"for":[5,90,125],"malware-family":[6],"classification,":[7],"but":[8],"their":[9],"value":[10],"must":[11],"be":[12],"assessed":[13],"against":[14],"simple":[15],"distributional":[16],"controls":[17],"under":[18],"a":[19,64],"shared":[20],"evaluation":[21],"protocol.":[22],"We":[23],"compare":[24],"globally":[25],"trained":[26],"Word2Vec,":[27,93],"GloVe,":[28,94],"and":[29,79,95],"fastText":[30,96],"embeddings":[31],"with":[32],"normalized":[33],"opcode":[34,91],"frequencies":[35],"on":[36,67,82,139],"1,045":[37],"files":[38],"from":[39],"nine":[40],"malware":[41],"families.":[42],"Ten":[43],"stratified":[44],"repeated":[45],"holdouts":[46],"use":[47],"identical":[48],"file":[49],"assignments":[50],"across":[51],"representations.":[52],"Embedding":[53],"epochs":[54],"are":[55],"selected":[56,141],"using":[57],"an":[58],"inner":[59],"validation":[60],"partition,":[61],"followed":[62],"by":[63],"fresh":[65],"fit":[66],"the":[68,83,109,131],"outer":[69],"training":[70,78],"files.":[71,86],"A":[72],"fixed":[73],"Random":[74],"Forest":[75],"evaluates":[76],"original-only":[77,88],"conventional":[80],"oversampling":[81],"same":[84],"held-out":[85],"Mean":[87],"accuracies":[89],"frequency,":[92,126],"were":[97],"1.0000,":[98],"0.9995,":[99],"0.9981,":[100],"0.9976,":[101],"respectively.":[102],"The":[103],"frequency":[104],"baseline":[105],"matched":[106],"or":[107],"exceeded":[108],"learned":[110],"representations\u2019":[111],"mean":[112],"accuracy.":[113],"SMOTE":[114],"increased":[115],"macro":[116],"F1":[117],"in":[118],"4":[119],"of":[120],"40":[121],"representation\u2013split":[122],"pairs":[123],"(none":[124],"which":[127],"was":[128],"already":[129],"at":[130],"ceiling).":[132],"All":[133],"four":[134],"achieved":[136],"near-ceiling":[137],"accuracy":[138],"this":[140],"closed-set":[142],"benchmark.":[143]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}