{"id":"https://openalex.org/W4382655549","doi":"https://doi.org/10.1109/svcc56964.2023.10165170","title":"Malware Detection through Contextualized Vector Embeddings","display_name":"Malware Detection through Contextualized Vector Embeddings","publication_year":2023,"publication_date":"2023-05-17","ids":{"openalex":"https://openalex.org/W4382655549","doi":"https://doi.org/10.1109/svcc56964.2023.10165170"},"language":"en","primary_location":{"id":"doi:10.1109/svcc56964.2023.10165170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/svcc56964.2023.10165170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Silicon Valley Cybersecurity Conference (SVCC)","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/A5037225563","display_name":"Vinay Pandya","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Pandya","raw_affiliation_strings":["San Jose State University,Department of Computer Science,San Jose,CA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Computer Science,San Jose,CA,U.S.A","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074325073","display_name":"Fabio Di Troia","orcid":"https://orcid.org/0000-0003-2355-7146"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabio Di Troia","raw_affiliation_strings":["San Jose State University,Department of Computer Science,San Jose,CA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Computer Science,San Jose,CA,U.S.A","institution_ids":["https://openalex.org/I51504820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62541785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9977999925613403,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9977999925613403,"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/opcode","display_name":"Opcode","score":0.9495455622673035},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.8725411891937256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8291904926300049},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8122169971466064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.638765275478363},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6094387769699097},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6017350554466248},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5448039770126343},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.536824643611908},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4588014483451843},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.42674940824508667},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4255126714706421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3893515169620514},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.1409812867641449},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10321792960166931},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08618155121803284}],"concepts":[{"id":"https://openalex.org/C52173422","wikidata":"https://www.wikidata.org/wiki/Q766483","display_name":"Opcode","level":2,"score":0.9495455622673035},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8725411891937256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291904926300049},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8122169971466064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.638765275478363},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6094387769699097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6017350554466248},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5448039770126343},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.536824643611908},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4588014483451843},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.42674940824508667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4255126714706421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3893515169620514},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.1409812867641449},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10321792960166931},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08618155121803284},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/svcc56964.2023.10165170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/svcc56964.2023.10165170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Silicon Valley Cybersecurity Conference (SVCC)","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":18,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2921244337","https://openalex.org/W2945009197","https://openalex.org/W2962739339","https://openalex.org/W2965373594","https://openalex.org/W2966634653","https://openalex.org/W2978017171","https://openalex.org/W2996428491","https://openalex.org/W3117786434","https://openalex.org/W3123408856","https://openalex.org/W3162090017","https://openalex.org/W3173300022","https://openalex.org/W4224305508","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6797244535"],"related_works":["https://openalex.org/W36091977","https://openalex.org/W4382794599","https://openalex.org/W2800331776","https://openalex.org/W2903602818","https://openalex.org/W2003791967","https://openalex.org/W4387382577","https://openalex.org/W3016048014","https://openalex.org/W4294976063","https://openalex.org/W2902612505","https://openalex.org/W2765921396"],"abstract_inverted_index":{"Detecting":[0],"malware":[1,44,123],"is":[2,30],"an":[3],"integral":[4],"part":[5],"of":[6,27,147],"system":[7],"security.":[8],"In":[9],"recent":[10],"years,":[11],"machine":[12,115],"learning":[13,116],"models":[14,117],"have":[15],"been":[16],"applied":[17],"with":[18,96,130],"success":[19],"to":[20,31,36,49,65,83,112],"overcome":[21],"this":[22,28,81],"challenging":[23],"problem.":[24],"The":[25,139],"aim":[26],"research":[29],"apply":[32],"context-dependent":[33,85],"word":[34,86],"embeddings":[35,52,109,132,145],"classify":[37],"malware.":[38],"We":[39,125],"extract":[40],"opcodes":[41],"from":[42,89,121],"the":[43,51,55],"samples":[45,120],"and":[46,76,136,156],"use":[47],"them":[48],"generate":[50,84,104],"that":[53,62],"train":[54,113],"classifiers.":[56],"Transformers":[57],"are":[58,78,110],"a":[59,98],"novel":[60],"architecture":[61],"utilizes":[63],"self-attention":[64],"handle":[66],"long-range":[67],"dependencies.":[68],"Different":[69],"transformer":[70,91],"architectures,":[71],"namely,":[72],"BERT,":[73],"DistilBERT,":[74],"AIBERT,":[75],"RoBERTa,":[77],"implemented":[79],"in":[80,118],"work":[82],"embeddings.":[87,107],"Apart":[88],"using":[90],"models,":[92],"we":[93],"also":[94],"experimented":[95],"ELMo,":[97],"bidirectional":[99],"language":[100],"model":[101],"which":[102],"can":[103],"contextualized":[105,128],"opcode":[106],"These":[108],"used":[111],"our":[114,127,144],"classifying":[119],"different":[122],"families.":[124],"compared":[126],"results":[129],"context-free":[131],"generated":[133],"by":[134],"Word2Vec,":[135],"HMM2Vec":[137],"algorithms.":[138],"classification":[140],"algorithms":[141],"trained":[142],"on":[143],"consist":[146],"Resnet-18":[148],"CNN,":[149],"Random":[150],"Forest,":[151],"Support":[152],"Vector":[153],"Machines":[154],"(SVMs),":[155],"k-Nearest":[157],"Neighbours":[158],"(k-NNs).":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}