{"id":"https://openalex.org/W4415936768","doi":"https://doi.org/10.48550/arxiv.2511.00342","title":"MH-1M: A 1.34 Million-Sample Comprehensive Multi-Feature Android Malware Dataset for Machine Learning, Deep Learning, Large Language Models, and Threat Intelligence Research","display_name":"MH-1M: A 1.34 Million-Sample Comprehensive Multi-Feature Android Malware Dataset for Machine Learning, Deep Learning, Large Language Models, and Threat Intelligence Research","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4415936768","doi":"https://doi.org/10.48550/arxiv.2511.00342"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.00342","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.00342","pdf_url":"https://arxiv.org/pdf/2511.00342","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.00342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002558458","display_name":"Hendrio Luis de Souza Bragan\u00e7a","orcid":"https://orcid.org/0000-0003-1479-1707","observed_orcids":["https://orcid.org/0000-0003-1479-1707"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Braganca, Hendrio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088960174","display_name":"Diego Kreutz","orcid":"https://orcid.org/0000-0003-0830-0238","observed_orcids":["https://orcid.org/0000-0003-0830-0238"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kreutz, Diego","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002600007","display_name":"Vanderson da Silva Rocha","orcid":"https://orcid.org/0000-0003-3103-7749","observed_orcids":["https://orcid.org/0000-0003-3103-7749"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rocha, Vanderson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044667102","display_name":"Joner Assolin","orcid":"https://orcid.org/0000-0001-8517-6600","observed_orcids":["https://orcid.org/0000-0001-8517-6600"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assolin, Joner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005634127","display_name":"Feitosa Eduardo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feitosa, and Eduardo","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":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/T11644","display_name":"Spam and Phishing Detection","score":0.0,"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/T10260","display_name":"Software Engineering Research","score":0.0,"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/android-malware","display_name":"Android malware","score":0.996999979019165},{"id":"https://openalex.org/keywords/malware-dataset","display_name":"malware dataset","score":0.8820000290870667},{"id":"https://openalex.org/keywords/malware-classification","display_name":"malware classification","score":0.7639999985694885},{"id":"https://openalex.org/keywords/mobile-security","display_name":"mobile security","score":0.503000020980835},{"id":"https://openalex.org/keywords/threat-intelligence","display_name":"threat intelligence","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8014000058174133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960000038146973},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C2989133298","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android malware","level":3,"score":0.548799991607666},{"id":"https://openalex.org/C84525096","wikidata":"https://www.wikidata.org/wiki/Q3506050","display_name":"Cryptovirology","level":3,"score":0.4510999917984009},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C3018725008","wikidata":"https://www.wikidata.org/wiki/Q4071928","display_name":"Cyber threats","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.00342","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.00342","pdf_url":"https://arxiv.org/pdf/2511.00342","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2511.00342","doi":"https://doi.org/10.48550/arxiv.2511.00342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.00342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.00342","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.00342","pdf_url":"https://arxiv.org/pdf/2511.00342","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117715315","https://openalex.org/W4402984117","https://openalex.org/W4388210610","https://openalex.org/W4391593938","https://openalex.org/W2953797486","https://openalex.org/W4396853082","https://openalex.org/W2620844046","https://openalex.org/W4281773819","https://openalex.org/W4416901687","https://openalex.org/W6925300172"],"abstract_inverted_index":{"We":[0],"present":[1],"MH-1M,":[2],"one":[3],"of":[4,25,73,79,104],"the":[5,37,60,77,80,87,94,101],"most":[6],"comprehensive":[7,45],"and":[8,27,46,52,63,75],"up-to-date":[9],"datasets":[10],"for":[11,44],"advanced":[12],"Android":[13],"malware":[14,33],"research.":[15],"The":[16],"dataset":[17,62],"comprises":[18],"1,340,515":[19],"applications,":[20],"encompassing":[21],"a":[22],"wide":[23],"range":[24],"features":[26],"extensive":[28,65],"metadata.":[29],"To":[30],"ensure":[31],"accurate":[32],"classification,":[34],"we":[35],"employ":[36],"VirusTotal":[38,89],"API,":[39],"integrating":[40],"multiple":[41],"detection":[42],"engines":[43],"reliable":[47],"assessment.":[48],"Our":[49,91],"GitHub,":[50],"Figshare,":[51],"Harvard":[53],"Dataverse":[54],"repositories":[55],"provide":[56],"open":[57],"access":[58],"to":[59],"processed":[61],"its":[64],"supplementary":[66],"metadata,":[67],"totaling":[68],"more":[69],"than":[70],"400":[71],"GB":[72],"data":[74],"including":[76],"outputs":[78],"feature":[81],"extraction":[82],"pipeline":[83],"as":[84,86],"well":[85],"corresponding":[88],"reports.":[90],"findings":[92],"underscore":[93],"MH-1M":[95],"dataset's":[96],"invaluable":[97],"role":[98],"in":[99],"understanding":[100],"evolving":[102],"landscape":[103],"malware.":[105]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-05T00:00:00"}
