{"id":"https://openalex.org/W7095030172","doi":"https://doi.org/10.21227/e08a-7p02","title":"\"APT-ClaritySet: A Large-Scale, High-Fidelity Labeled Dataset for APT Malware\"","display_name":"\"APT-ClaritySet: A Large-Scale, High-Fidelity Labeled Dataset for APT Malware\"","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7095030172","doi":"https://doi.org/10.21227/e08a-7p02"},"language":null,"primary_location":{"id":"doi:10.21227/e08a-7p02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/e08a-7p02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/e08a-7p02","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhenhao Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhenhao Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12532","display_name":"Historical and Cultural Archaeology Studies","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12532","display_name":"Historical and Cultural Archaeology Studies","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13863","display_name":"Cultural History and Identity Formation","score":0.03610000014305115,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13750","display_name":"Mormonism, Religion, and History","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6047000288963318},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5375999808311462},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.3560999929904938},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.31700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/e08a-7p02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/e08a-7p02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/e08a-7p02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/e08a-7p02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"\"Large-scale,":[0],"standardized":[1,80],"datasets":[2],"for":[3,119],"AdvancedPersistent":[4],"Threat":[5],"(APT)":[6],"research":[7],"are":[8],"scarce,":[9],"and":[10,13,21,34,79,82,99,105,109,125],"inconsistentactor":[11],"aliases":[12,28],"redundant":[14],"samples":[15,61],"hinder":[16],"reproducibility.":[17],"Thispaper":[18],"presents":[19],"APT-ClaritySet":[20,50],"its":[22],"construction":[23],"pipelinethat":[24],"normalizes":[25],"threat":[26],"actor":[27],"(reconciling":[29],"approximately11.22%":[30],"of":[31,40,95,121],"inconsistent":[32],"names)":[33],"applies":[35],"graph-feature":[36],"dedu-plication\\u2014reducing":[37],"the":[38,54,70,107],"subset":[39],"statically":[41],"analyzable":[42],"executablesby":[43],"47.55%":[44],"while":[45],"retaining":[46],"behaviorally":[47],"distinct":[48],"variants.":[49],"comprises:":[51],"(i)":[52],"APT-ClaritySet-Full,":[53],"complete":[55],"pre-deduplication":[56],"collection":[57],"with":[58,73],"34,363":[59],"malware":[60],"attributedto":[62],"305":[63],"APT":[64,122],"groups":[65,78],"(2006\\u2013early":[66],"2025);":[67],"(ii)":[68],"APT-ClaritySet-Unique,":[69],"deduplicated":[71],"release":[72],"25,923":[74],"unique":[75],"samplesspanning":[76],"303":[77],"attributions;":[81],"(iii)APT-ClaritySet-FuncReuse,":[83],"a":[84,115],"function-level":[85],"resource":[86],"that":[87],"in-cludes":[88],"324,538":[89],"function-reuse":[90],"clusters":[91],"(FRCs)":[92],"enabling":[93],"mea-surement":[94],"inter-\\/intra-group":[96],"sharing,":[97],"evolution,":[98,124],"toolinglineage.":[100],"By":[101],"releasing":[102],"these":[103],"components":[104],"detailing":[106],"aliasnormalization":[108],"scalable":[110],"deduplication":[111],"pipeline,":[112],"this":[113],"workprovides":[114],"high-fidelity,":[116],"reproducible":[117],"foundation":[118],"quantitativestudies":[120],"patterns,":[123],"attribution.\"":[126]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-27T00:00:00"}
