{"id":"https://openalex.org/W7165913747","doi":"https://doi.org/10.1109/access.2026.3707213","title":"RIT-PDFMal-2026: A Comprehensive Benchmark Dataset for PDF Malware Detection","display_name":"RIT-PDFMal-2026: A Comprehensive Benchmark Dataset for PDF Malware Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165913747","doi":"https://doi.org/10.1109/access.2026.3707213"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3707213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3707213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3707213","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034542641","display_name":"Mohammed M. Alani","orcid":"https://orcid.org/0000-0002-4324-1774"},"institutions":[{"id":"https://openalex.org/I109703491","display_name":"Rochester Institute of Technology - Dubai","ror":"https://ror.org/03zmfa837","country_code":"AE","type":"education","lineage":["https://openalex.org/I109703491"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohammed M. Alani","raw_affiliation_strings":["Rochester Institute of Technology of Dubai, Dubai, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-4324-1774","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology of Dubai, Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I109703491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075830877","display_name":"Ernesto Damiani","orcid":"https://orcid.org/0000-0002-9557-6496"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ernesto Damiani","raw_affiliation_strings":["Universit&#x00E0; degli Studi di Milano, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9557-6496","affiliations":[{"raw_affiliation_string":"Universit&#x00E0; degli Studi di Milano, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85046113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"97841","last_page":"97855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9581999778747559,"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":0.9581999778747559,"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/T11644","display_name":"Spam and Phishing Detection","score":0.01119999960064888,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.003700000001117587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7236999869346619},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7013000249862671},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3246000111103058},{"id":"https://openalex.org/keywords/electronic-mail","display_name":"Electronic mail","score":0.2703000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392000198364258},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7236999869346619},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7013000249862671},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.24639999866485596}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3707213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3707213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8acdab5e2d354c36971d274042addb66","is_oa":false,"landing_page_url":"https://doaj.org/article/8acdab5e2d354c36971d274042addb66","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,"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":"IEEE Access, Vol 14, Pp 97841-97855 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3707213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3707213","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3118089521","display_name":null,"funder_award_id":"RITD-ARC-2025-001","funder_id":"https://openalex.org/F4320316118","funder_display_name":"Rochester Institute of Technology"}],"funders":[{"id":"https://openalex.org/F4320316118","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Portable":[0],"Document":[1],"Format":[2],"(PDF)":[3],"has":[4],"gained":[5],"rapid":[6],"popularity":[7,44],"in":[8,33,123,165],"the":[9,26,115,124,141,170,180,187,190],"past":[10],"two":[11],"decades":[12],"due":[13],"to":[14,29,82,113,178],"its":[15],"platform-independence,":[16],"and":[17,41,79,90,126,185],"portability.":[18],"A":[19],"single":[20],"PDF":[21,46,67,96,111,150],"file":[22],"can":[23],"contain":[24],"all":[25],"elements":[27],"needed":[28],"convey":[30],"a":[31,34,60,73,84,129],"document":[32],"fixed":[35],"format,":[36],"such":[37],"as":[38],"text,":[39],"images,":[40],"fonts.":[42],"This":[43],"made":[45],"documents":[47],"an":[48,103],"important":[49],"attack":[50],"vector":[51],"for":[52,66,88],"malicious":[53,78,95,149],"activity.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"present":[59],"comprehensive,":[61],"carefully":[62],"curated":[63],"benchmark":[64],"dataset":[65,71,86,120],"malware":[68],"detection.":[69],"The":[70,99,118,136,159],"captures":[72],"large":[74],"number":[75],"of":[76,92,106,128,131,147,189],"real-life":[77],"benign":[80],"samples":[81],"build":[83],"24,337-samples":[85],"suitable":[87],"training":[89,125],"testing":[91,127,137],"machine":[93,133],"learning-based":[94],"detection":[97,116],"systems.":[98],"work":[100],"also":[101,161],"presents":[102],"extended":[104],"set":[105],"static":[107],"features":[108],"extracted":[109],"from":[110],"files":[112],"support":[114],"process.":[117],"presented":[119],"was":[121,145,172],"used":[122],"pipeline":[130],"different":[132],"learning":[134],"classifiers.":[135],"results":[138],"showed":[139],"that":[140],"extreme":[142],"gradient-boost":[143],"classifier":[144,191],"capable":[146],"detecting":[148],"with":[151,193],"<inline-formula>":[152],"<tex-math":[153],"notation=\"LaTeX\">$F_{1}$":[154],"</tex-math></inline-formula>":[155],"score":[156],"exceeding":[157],"0.99.":[158],"model":[160,171],"performed":[162],"similarly":[163],"well":[164],"10-fold":[166],"cross":[167],"validation.":[168],"Additionally,":[169],"explained":[173],"using":[174],"Shapley":[175],"additive":[176],"explanation":[177],"ensure":[179,186],"model&#x2019;s":[181],"transparency,":[182],"increase":[183],"confidence,":[184],"alignment":[188],"decision":[192],"human":[194],"experience.":[195]},"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-06-26T00:00:00"}