{"id":"https://openalex.org/W4402659630","doi":"https://doi.org/10.1145/3685650.3685668","title":"An Efficient PDF Malware Detection Method Using Highly Compact Features","display_name":"An Efficient PDF Malware Detection Method Using Highly Compact Features","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4402659630","doi":"https://doi.org/10.1145/3685650.3685668"},"language":"en","primary_location":{"id":"doi:10.1145/3685650.3685668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3685650.3685668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2024","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102848036","display_name":"Ran Liu","orcid":"https://orcid.org/0009-0008-6870-7543"},"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":"Ran Liu","raw_affiliation_strings":["Univ. of Maryland, Baltimore County"],"raw_orcid":"https://orcid.org/0009-0008-6870-7543","affiliations":[{"raw_affiliation_string":"Univ. of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019767181","display_name":"Cynthia Matuszek","orcid":"https://orcid.org/0000-0003-1383-8120"},"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":"Cynthia Matuszek","raw_affiliation_strings":["Univ. of Maryland, Baltimore County"],"raw_orcid":"https://orcid.org/0000-0003-1383-8120","affiliations":[{"raw_affiliation_string":"Univ. of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"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":["Univ. of Maryland, Baltimore County"],"raw_orcid":"https://orcid.org/0000-0001-9494-7139","affiliations":[{"raw_affiliation_string":"Univ. of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.4171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55735024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9988999962806702,"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":0.9972000122070312,"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/malware","display_name":"Malware","score":0.7511636018753052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6964210271835327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3477434515953064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.322720468044281},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.24230599403381348}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7511636018753052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964210271835327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3477434515953064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.322720468044281},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.24230599403381348}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3685650.3685668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3685650.3685668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2024","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":12,"referenced_works":["https://openalex.org/W2038296020","https://openalex.org/W2082190528","https://openalex.org/W2144906988","https://openalex.org/W2151298633","https://openalex.org/W2296452361","https://openalex.org/W2525598640","https://openalex.org/W2573650634","https://openalex.org/W2574797807","https://openalex.org/W2897893551","https://openalex.org/W3111818035","https://openalex.org/W4288104392","https://openalex.org/W4391095620"],"related_works":["https://openalex.org/W4391375266","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/W4284893819","https://openalex.org/W2249809453"],"abstract_inverted_index":{"The":[0],"growing":[1],"use":[2],"of":[3,34,42,68,81],"PDFs":[4],"has":[5],"made":[6],"them":[7],"a":[8,60,116],"prime":[9],"target":[10],"for":[11,17],"malware":[12,20,83],"attacks.":[13,56],"Machine":[14],"learning-based":[15],"approaches":[16],"detecting":[18],"PDF":[19,82],"are":[21],"increasingly":[22],"popular":[23],"due":[24],"to":[25,73],"their":[26],"high":[27],"accuracy":[28],"and":[29,45,77],"efficiency.":[30],"However,":[31],"the":[32,40,43,46,79,91,112,122],"effectiveness":[33],"these":[35],"systems":[36],"largely":[37],"depends":[38],"on":[39,90],"quality":[41],"dataset":[44],"features":[47],"used.":[48],"Additionally,":[49],"they":[50],"face":[51],"challenges":[52],"from":[53],"sophisticated":[54],"evasion":[55],"This":[57],"paper":[58],"introduces":[59],"compact":[61],"yet":[62],"highly":[63,106],"effective":[64],"feature":[65,101],"set,":[66],"consisting":[67],"just":[69],"five":[70],"features,":[71],"designed":[72],"improve":[74],"training":[75],"efficiency":[76],"enhance":[78],"robustness":[80,114],"detection":[84,93],"models.":[85],"Through":[86],"experiments,":[87],"including":[88],"tests":[89],"real-world":[92],"system":[94],"PDFRATE,":[95],"we":[96],"demonstrate":[97],"that":[98],"our":[99],"proposed":[100],"set":[102],"not":[103],"only":[104],"trains":[105],"accurate":[107],"models":[108],"but":[109],"also":[110],"increases":[111],"system's":[113],"against":[115],"specific":[117],"evasive":[118],"attack":[119],"known":[120],"as":[121],"Benign":[123],"Random":[124],"Noise":[125],"(BRN)":[126],"attack.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}