{"id":"https://openalex.org/W4224253745","doi":"https://doi.org/10.3390/app12084088","title":"Classifying Malicious Documents on the Basis of Plain-Text Features: Problem, Solution, and Experiences","display_name":"Classifying Malicious Documents on the Basis of Plain-Text Features: Problem, Solution, and Experiences","publication_year":2022,"publication_date":"2022-04-18","ids":{"openalex":"https://openalex.org/W4224253745","doi":"https://doi.org/10.3390/app12084088"},"language":"en","primary_location":{"id":"doi:10.3390/app12084088","doi":"https://doi.org/10.3390/app12084088","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app12084088","pdf_url":"https://www.mdpi.com/2076-3417/12/8/4088/pdf?version=1650287321","source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2076-3417/12/8/4088/pdf?version=1650287321","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038728451","display_name":"Jiwon Hong","orcid":"https://orcid.org/0000-0001-8664-3258","observed_orcids":["https://orcid.org/0000-0001-8664-3258"]},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwon Hong","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul 04763, Korea"],"raw_orcid":"https://orcid.org/0000-0001-8664-3258","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul 04763, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080103296","display_name":"Dongho Jeong","orcid":"https://orcid.org/0000-0001-5988-3301","observed_orcids":["https://orcid.org/0000-0001-5988-3301"]},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongho Jeong","raw_affiliation_strings":["Department of Artificial Intelligence, Hanyang University, Seoul 04763, Korea"],"raw_orcid":"https://orcid.org/0000-0001-5988-3301","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Hanyang University, Seoul 04763, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100656150","display_name":"Sang\u2010Wook Kim","orcid":"https://orcid.org/0000-0002-6345-9084","observed_orcids":["https://orcid.org/0000-0002-6345-9084","https://orcid.org/0000-0002-8264-0866"]},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sang-Wook Kim","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul 04763, Korea"],"raw_orcid":"https://orcid.org/0000-0002-6345-9084","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul 04763, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100656150"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":2300,"currency":"CHF","value_usd":2408},"apc_paid":{"value":2300,"currency":"CHF","value_usd":2408},"fwci":0.8617,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76217935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"12","issue":"8","first_page":"4088","last_page":"4088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.44190001487731934,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.44190001487731934,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.41670000553131104,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.10249999910593033,"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/malware-detection","display_name":"malware detection","score":0.5889999866485596},{"id":"https://openalex.org/keywords/electronic-documents","display_name":"electronic documents","score":0.8410000205039978},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.6869999766349792},{"id":"https://openalex.org/keywords/cyberattacks","display_name":"cyberattacks","score":0.5830000042915344},{"id":"https://openalex.org/keywords/malware","display_name":"malware","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759334444999695},{"id":"https://openalex.org/C92717368","wikidata":"https://www.wikidata.org/wiki/Q1162538","display_name":"Plaintext","level":3,"score":0.6522496342658997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6027230620384216},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.517983078956604},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5078919529914856},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.43097811937332153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39342257380485535},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20750153064727783},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.13666841387748718},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07069018483161926},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/app12084088","doi":"https://doi.org/10.3390/app12084088","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app12084088","pdf_url":"https://www.mdpi.com/2076-3417/12/8/4088/pdf?version=1650287321","source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b8e8a41d1d2240b79b88a299f455defb","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/b8e8a41d1d2240b79b88a299f455defb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Sciences, Vol 12, Iss 8, p 4088 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/app12084088","doi":"https://doi.org/10.3390/app12084088","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app12084088","pdf_url":"https://www.mdpi.com/2076-3417/12/8/4088/pdf?version=1650287321","source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224253745.pdf","grobid_xml":"https://content.openalex.org/works/W4224253745.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1680392829","https://openalex.org/W1811029946","https://openalex.org/W1836465849","https://openalex.org/W1972640883","https://openalex.org/W1978394996","https://openalex.org/W1980558234","https://openalex.org/W1988790447","https://openalex.org/W1990351156","https://openalex.org/W1993651556","https://openalex.org/W2034978228","https://openalex.org/W2076063813","https://openalex.org/W2082190528","https://openalex.org/W2095705004","https://openalex.org/W2110143557","https://openalex.org/W2112076978","https://openalex.org/W2125283600","https://openalex.org/W2131904035","https://openalex.org/W2144211451","https://openalex.org/W2146424733","https://openalex.org/W2149706766","https://openalex.org/W2153439141","https://openalex.org/W2153579005","https://openalex.org/W2163922914","https://openalex.org/W2327361494","https://openalex.org/W2605860169","https://openalex.org/W2732916693","https://openalex.org/W2759474451","https://openalex.org/W2787894218","https://openalex.org/W2800367525","https://openalex.org/W2802022891","https://openalex.org/W2882319491","https://openalex.org/W2895892359","https://openalex.org/W2912934387","https://openalex.org/W2937423263","https://openalex.org/W2972552958","https://openalex.org/W3012124607","https://openalex.org/W3013896538","https://openalex.org/W3080622597","https://openalex.org/W3116565206","https://openalex.org/W3135185324","https://openalex.org/W3163821226","https://openalex.org/W3196715586","https://openalex.org/W3214686023","https://openalex.org/W4236122429"],"related_works":["https://openalex.org/W3081186231","https://openalex.org/W2923724895","https://openalex.org/W2779064420","https://openalex.org/W1522552151","https://openalex.org/W2082190528","https://openalex.org/W4404340448","https://openalex.org/W2974989311","https://openalex.org/W2000596749","https://openalex.org/W2312936843","https://openalex.org/W4280582787"],"abstract_inverted_index":{"Cyberattacks":[0],"widely":[1],"occur":[2],"by":[3],"using":[4],"malicious":[5,8,15,68,103],"documents.":[6,69,104],"A":[7],"document":[9,13,45],"is":[10,23,46],"an":[11],"electronic":[12,56,91],"containing":[14],"codes":[16],"along":[17],"with":[18,74],"some":[19],"plain-text":[20],"data":[21,39],"that":[22,33,94],"human-readable.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"a":[30,43,63],"novel":[31],"framework":[32,96],"takes":[34],"advantage":[35],"of":[36,55,77,90],"such":[37],"plaintext":[38,50],"to":[40,61],"determine":[41],"whether":[42],"given":[44],"malicious.":[47],"We":[48],"extracted":[49],"features":[51],"from":[52],"the":[53],"corpus":[54],"documents":[57,92],"and":[58,82],"utilized":[59],"them":[60],"train":[62],"classification":[64,85],"model":[65],"for":[66],"detecting":[67,102],"Our":[70],"extensive":[71],"experimental":[72],"results":[73],"different":[75],"combinations":[76],"three":[78,83],"well-known":[79],"vectorization":[80],"strategies":[81],"popular":[84],"methods":[86],"on":[87],"five":[88],"types":[89],"demonstrate":[93],"our":[95],"provides":[97],"high":[98],"prediction":[99],"accuracy":[100],"in":[101]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2022-04-26T00:00:00"}
