{"id":"https://openalex.org/W4392248300","doi":"https://doi.org/10.1109/icce59016.2024.10444433","title":"An Advanced Malware Detection System Based on NLP to Generate Genetic Markers","display_name":"An Advanced Malware Detection System Based on NLP to Generate Genetic Markers","publication_year":2024,"publication_date":"2024-01-06","ids":{"openalex":"https://openalex.org/W4392248300","doi":"https://doi.org/10.1109/icce59016.2024.10444433"},"language":"en","primary_location":{"id":"doi:10.1109/icce59016.2024.10444433","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","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/A5007268081","display_name":"Quang Duy Tran","orcid":"https://orcid.org/0000-0002-3639-2179"},"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":true,"raw_author_name":"Quang Duy Tran","raw_affiliation_strings":["San Jose State University,Department of Computer Science,CA,USA","Department of Computer Science, San Jose State University, CA, USA"],"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Computer Science,CA,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Computer Science, San Jose State University, CA, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025037378","display_name":"Jae-Hyun Lim","orcid":"https://orcid.org/0000-0001-7169-8969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehyun Lim","raw_affiliation_strings":["Silicon Valley Cybersecurity Institute,Saratoga High School","Saratoga High School, Silicon Valley Cybersecurity Institute"],"affiliations":[{"raw_affiliation_string":"Silicon Valley Cybersecurity Institute,Saratoga High School","institution_ids":[]},{"raw_affiliation_string":"Saratoga High School, Silicon Valley Cybersecurity Institute","institution_ids":[]}]},{"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,CA,USA","San Jose State University, CA, USA","Silicon Valley Cybersecurity Institute"],"affiliations":[{"raw_affiliation_string":"San Jose State University,CA,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"San Jose State University, CA, USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Silicon Valley Cybersecurity Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007268081"],"corresponding_institution_ids":["https://openalex.org/I51504820"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01907085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"6"},"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":0.9987000226974487,"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":0.9876999855041504,"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/computer-science","display_name":"Computer science","score":0.8326109647750854},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.8260087370872498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6763569116592407},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6359542608261108},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09862956404685974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8326109647750854},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8260087370872498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6763569116592407},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6359542608261108},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09862956404685974}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce59016.2024.10444433","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","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":22,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1995341919","https://openalex.org/W2004147962","https://openalex.org/W2037109870","https://openalex.org/W2082550445","https://openalex.org/W2095577883","https://openalex.org/W2131744502","https://openalex.org/W2171035369","https://openalex.org/W2255223209","https://openalex.org/W2539582590","https://openalex.org/W2782791108","https://openalex.org/W2799784398","https://openalex.org/W2890822693","https://openalex.org/W2911964244","https://openalex.org/W2996806689","https://openalex.org/W2999237896","https://openalex.org/W3126643594","https://openalex.org/W4224305508","https://openalex.org/W4239510810","https://openalex.org/W6636510571","https://openalex.org/W6679775712","https://openalex.org/W6811515478"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2097492617","https://openalex.org/W2753240997","https://openalex.org/W1764168690","https://openalex.org/W2537959205","https://openalex.org/W2740895074","https://openalex.org/W2772446090","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Malware":[0],"researchers":[1],"are":[2],"increasingly":[3],"employing":[4,114],"machine":[5,19,40,84,138],"learning":[6,20,41,45,85,135,139],"to":[7],"counter":[8],"sophisticated":[9],"obfuscation":[10],"techniques":[11],"in":[12,43,103,142],"malware":[13,25,49,76,108,122],"activities.":[14],"However,":[15],"relying":[16],"solely":[17],"on":[18],"models,":[21,140],"especially":[22],"with":[23],"limited":[24],"samples,":[26],"is":[27,36],"suboptimal.":[28],"To":[29,38],"enhance":[30],"model":[31],"effectiveness,":[32],"careful":[33],"data":[34],"preprocessing":[35],"essential.":[37],"aid":[39],"models":[42,119],"their":[44],"process,":[46],"we":[47],"disassembled":[48],"binary":[50],"files":[51],"into":[52],"mnemonic":[53],"opcode":[54,80],"sequences":[55],"and":[56,65,97,117],"leveraging":[57],"insights":[58],"from":[59],"Natural":[60],"Language":[61],"Processing,":[62],"specifically":[63],"Word2Vec":[64,116],"Doc2Vec.":[66],"This":[67,131],"methodology":[68],"generates":[69],"\u201cgenetic":[70,129],"markers\u201d":[71],"proficient":[72],"at":[73],"capturing":[74],"inherent":[75],"attributes,":[77],"effectively":[78],"bypassing":[79],"obfuscation.":[81],"Using":[82],"various":[83],"models\u2014Naive":[86],"Bayes,":[87],"Logistic":[88],"Regression,":[89],"Support":[90],"Vector":[91],"Machine,":[92],"Random":[93],"Forest,":[94],"Multi-layer":[95],"Perceptron,":[96],"Convolutional":[98],"biLSTM\u2014we":[99],"achieve":[100],"promising":[101],"results":[102],"distinguishing":[104],"among":[105],"20":[106],"discrete":[107],"families.":[109],"Our":[110],"findings":[111],"reveal":[112],"that":[113],"customized":[115],"Doc2Vec":[118],"for":[120],"distinct":[121],"family":[123],"datasets":[124],"enhances":[125],"the":[126,134],"precision":[127],"of":[128,137,147],"markers.\u201d":[130],"refinement":[132],"boosts":[133],"capabilities":[136],"resulting":[141],"a":[143],"robust":[144],"detection":[145],"rate":[146],"99%.":[148]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}