{"id":"https://openalex.org/W4412876938","doi":"https://doi.org/10.1145/3711896.3737431","title":"EMBER2024 - A Benchmark Dataset for Holistic Evaluation of Malware Classifiers","display_name":"EMBER2024 - A Benchmark Dataset for Holistic Evaluation of Malware Classifiers","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876938","doi":"https://doi.org/10.1145/3711896.3737431"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737431","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737431","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008388322","display_name":"Robert J. Joyce","orcid":"https://orcid.org/0009-0003-7168-1237"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert J. Joyce","raw_affiliation_strings":["Booz Allen Hamilton, McLean, VA, USA"],"raw_orcid":"https://orcid.org/0009-0003-7168-1237","affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103466092","display_name":"Gerald R. Miller","orcid":"https://orcid.org/0009-0002-2561-3535"},"institutions":[{"id":"https://openalex.org/I4210113003","display_name":"Physical Sciences (United States)","ror":"https://ror.org/021qvjc46","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gideon Miller","raw_affiliation_strings":["Laboratory for Physical Sciences, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0009-0002-2561-3535","affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences, College Park, MD, USA","institution_ids":["https://openalex.org/I4210113003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085064312","display_name":"Phil Roth","orcid":null},"institutions":[{"id":"https://openalex.org/I2799992204","display_name":"Crowder College","ror":"https://ror.org/04t99en88","country_code":"US","type":"education","lineage":["https://openalex.org/I2799992204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phil Roth","raw_affiliation_strings":["CrowdStrike, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0009-0008-5404-4320","affiliations":[{"raw_affiliation_string":"CrowdStrike, Austin, TX, USA","institution_ids":["https://openalex.org/I2799992204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048807150","display_name":"Richard Zak","orcid":"https://orcid.org/0000-0003-4272-2565"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Zak","raw_affiliation_strings":["Booz Allen Hamilton, McLean, VA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4272-2565","affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030609209","display_name":"Elliott Zaresky-Williams","orcid":"https://orcid.org/0000-0003-4023-3880"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliott Zaresky-Williams","raw_affiliation_strings":["Booz Allen Hamilton, McLean, VA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4023-3880","affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005817824","display_name":"Hyrum S. Anderson","orcid":"https://orcid.org/0009-0009-4720-6907"},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyrum Anderson","raw_affiliation_strings":["Cisco Systems, San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-4720-6907","affiliations":[{"raw_affiliation_string":"Cisco Systems, San Jose, CA, USA","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Booz Allen Hamilton, McLean, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9900-1972","affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, McLean, VA, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102861683","display_name":"James Holt","orcid":"https://orcid.org/0000-0002-6368-8696"},"institutions":[{"id":"https://openalex.org/I4210113003","display_name":"Physical Sciences (United States)","ror":"https://ror.org/021qvjc46","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Holt","raw_affiliation_strings":["Laboratory for Physical Sciences, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-6368-8696","affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences, College Park, MD, USA","institution_ids":["https://openalex.org/I4210113003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5008388322"],"corresponding_institution_ids":["https://openalex.org/I1322124587"],"apc_list":null,"apc_paid":null,"fwci":9.7513,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98459969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5516","last_page":"5526"},"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":0.9976999759674072,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9674999713897705,"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":0.8446388244628906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512035369873047},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.724207878112793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5714700222015381},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43838271498680115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3247339725494385},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10764962434768677},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05767884850502014},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0513189435005188}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8446388244628906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512035369873047},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.724207878112793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5714700222015381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43838271498680115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3247339725494385},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10764962434768677},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05767884850502014},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0513189435005188}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3737431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737431","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737431","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.05074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05074","pdf_url":"https://arxiv.org/pdf/2506.05074","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737431","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737431","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876938.pdf","grobid_xml":"https://content.openalex.org/works/W4412876938.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1893133781","https://openalex.org/W1981221397","https://openalex.org/W2000159976","https://openalex.org/W2021963610","https://openalex.org/W2099053789","https://openalex.org/W2144112223","https://openalex.org/W2912095101","https://openalex.org/W2980212355","https://openalex.org/W3023980642","https://openalex.org/W3128485327","https://openalex.org/W4296068317","https://openalex.org/W4390306850"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"A":[0],"lack":[1],"of":[2,46,76,85,116,143,153,198],"accessible":[3],"data":[4],"has":[5],"historically":[6],"restricted":[7],"malware":[8,47,61,77,122,126,128,132,200],"analysis":[9],"research,":[10],"and":[11,50,87,97,114,131,192],"practitioners":[12],"have":[13,40],"relied":[14],"heavily":[15],"on":[16,120],"datasets":[17,26],"provided":[18],"by":[19,29,150],"industry":[20],"sources":[21],"to":[22,54,139,160,189],"advance.":[23],"Existing":[24],"public":[25],"are":[27,184],"limited":[28],"narrow":[30],"scope":[31],"-":[32],"most":[33],"include":[34,140],"files":[35,58,104,145],"targeting":[36],"a":[37,69,141,151,157],"single":[38],"platform,":[39],"labels":[41,98],"supporting":[42],"just":[43],"one":[44],"type":[45],"classification":[48,123],"task,":[49],"make":[51,60],"no":[52],"effort":[53],"capture":[55],"the":[56,83,89,112,137,186,196],"evasive":[57,165],"that":[59,72,146],"detection":[62],"difficult":[63],"in":[64,80,195],"practice.":[65],"We":[66,183],"present":[67],"EMBER2024,":[68],"new":[70,180,199],"dataset":[71,91,110,188],"enables":[73],"holistic":[74],"evaluation":[75,115],"classifiers.":[78],"Created":[79],"collaboration":[81],"with":[82,175],"authors":[84],"EMBER2017":[86],"EMBER2018,":[88],"EMBER2024":[90,135,187],"includes":[92],"hashes,":[93],"metadata,":[94],"feature":[95,172,181],"vectors,":[96],"for":[99,178],"more":[100],"than":[101],"3.2":[102],"million":[103],"from":[105],"six":[106],"file":[107],"formats.":[108],"Our":[109],"supports":[111],"training":[113],"machine":[117],"learning":[118],"models":[119],"seven":[121],"tasks,":[124],"including":[125],"detection,":[127],"family":[129],"classification,":[130],"behavior":[133],"identification.":[134],"is":[136],"first":[138],"collection":[142],"malicious":[144],"initially":[147],"went":[148],"undetected":[149],"set":[152,159],"antivirus":[154],"products,":[155],"creating":[156],"''challenge''":[158],"assess":[161],"classifier":[162],"performance":[163],"against":[164],"malware.":[166],"This":[167],"work":[168],"also":[169],"introduces":[170],"EMBER":[171],"version":[173],"3,":[174],"added":[176],"support":[177],"several":[179],"types.":[182],"releasing":[185],"promote":[190],"reproducibility":[191],"empower":[193],"researchers":[194],"pursuit":[197],"research":[201],"topics.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}