{"status":"OK","data":{"id":633495,"identifier":"XV84Z8","persistentUrl":"https://doi.org/10.34894/XV84Z8","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2026-04-29","storageIdentifier":"surf://10.34894/XV84Z8","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9989,"datasetType":"dataset","locks":[],"latestVersion":{"id":34367,"datasetId":633495,"datasetPersistentId":"doi:10.34894/XV84Z8","datasetType":"dataset","storageIdentifier":"surf://10.34894/XV84Z8","versionNumber":1,"internalVersionNumber":21,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2026-04-29T08:31:50Z","releaseTime":"2026-04-29T08:31:50Z","createTime":"2026-04-23T07:23:13Z","publicationDate":"2026-04-29","citationDate":"2026-04-29","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9989,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://i.creativecommons.org/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Android Datasets: Integration of VirusTotal and Quark-Engine Intelligence"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Mohsen, Fadi"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-3876-5781"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Zhang, Yulin"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/00jmfr291","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","@type":"https://schema.org/Organization"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Gultekin, Ali Murat"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/049asqa32","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","@type":"https://schema.org/Organization"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Bisgin, Halil"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/01c3xc117","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","@type":"https://schema.org/Organization"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Buchta, Koerner"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/00jmfr291","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","@type":"https://schema.org/Organization"}}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Mohsen, Fadi"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"rug.nl"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"The datasets shared here are derived from an existing dataset (https://doi.org/10.34894/H0YJFT) containing 870,515 applications with 48 metadata features. We enriched this original dataset using external malware intelligence from VirusTotal Premium v3 Enterprise and Quark-Engine 25.3.1.\n\nOf the 870,515 original apps:\n- 803,320 apps (92.3%) were matched to VirusTotal reports.\n- 772,732 apps (88.8%) were successfully scanned by Quark-Engine.\n- 772,533 apps (88.7%) had paired analyses from both sources.\n\nBased on this new intelligence, we generated new datasets that include parsed versions of the VirusTotal and Quark-Engine reports. Specifically, we enriched the original dataset with 10 new features (5 from Quark-Engine reports and 5 from VirusTotal). We also revalidated the original class label, producing 5 new validated datasets based on different VirusTotal detection thresholds.\n\nWe are also sharing parsed versions of both the VirusTotal and Quark-Engine reports."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2026-04-23"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science","Other"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Large dataset of Android apps"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Android security"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Threat-intelligence enrichment"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Dataset validation"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"VirusTotal"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Quark Engine"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Dataset reliability"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Mohsen, Fadi"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-04-23"},{"typeName":"dateOfCollection","multiple":true,"typeClass":"compound","value":[{"dateOfCollectionStart":{"typeName":"dateOfCollectionStart","multiple":false,"typeClass":"primitive","value":"2026-03-1"},"dateOfCollectionEnd":{"typeName":"dateOfCollectionEnd","multiple":false,"typeClass":"primitive","value":"2026-05-30"}}]},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["CSV"]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/XV84Z8"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:2b8eb54b-5ac4-42ed-bb5d-599e832a5a9c"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-cfe0d4eb-aa74-481d-b9e3-087cc44e1d5b"}]}},"files":[{"description":"The README file of this repository.","label":"descriptions.txt","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634174,"persistentId":"","filename":"descriptions.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":5293,"description":"The README file of this repository.","storageIdentifier":"surf://store:19dbaea099b-e129b48a860a","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"92d81f9f10e3400dc63dd5113e0a6331fe38b65b"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"This file is the mapping table that links application package names (pkgname) to MD5 hashes.","label":"md5_hashes.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634175,"persistentId":"","filename":"md5_hashes.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":102115997,"description":"This file is the mapping table that links application package names (pkgname) to MD5 hashes.","storageIdentifier":"surf://store:19dbaec0821-9f912e515866","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"b210a516f607d2451acc42254f6bc787ab3dc8ba"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"This file contains the original dataset with minor corrections. We found a bug in the parsing script that was previously used. We fixed the bug and generated a new CSV file ","label":"original_dataset_corrected.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":633892,"persistentId":"","filename":"original_dataset_corrected.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":206942879,"description":"This file contains the original dataset with minor corrections. We found a bug in the parsing script that was previously used. We fixed the bug and generated a new CSV file ","storageIdentifier":"surf://store:19dbaa82a32-57d96a890609","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"19d39e1ebbc74299874da345f103894d665c80d2"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"The original dataset + 10 new features (5 from VirusTotal and 5 from QuarkEngine)","label":"paper_summary_dataset.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":633910,"persistentId":"","filename":"paper_summary_dataset.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":242386344,"description":"The original dataset + 10 new features (5 from VirusTotal and 5 from QuarkEngine)","storageIdentifier":"surf://store:19dbaab4a04-f5d42ed12030","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"6105f85c1b32cd0be5f9c7f0ec98812e7924398c"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"This file contains the extensive feature set extracted from Quark Engine reports. ","label":"qk_extensive_features.zip","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634181,"persistentId":"","filename":"qk_extensive_features.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":349652410,"description":"This file contains the extensive feature set extracted from Quark Engine reports. ","storageIdentifier":"surf://store:19dbb1c15ea-219d545e1bc4","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"b33c4188885991da5b6bef60518b505ef6b2d36d"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"Validated dataset 1 using VirustTotal threshold 1","label":"val_dataset_t1.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634178,"persistentId":"","filename":"val_dataset_t1.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":25919040,"description":"Validated dataset 1 using VirustTotal threshold 1","storageIdentifier":"surf://store:19dbaecd255-a0e858add07d","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"711922f9f6e085910f0a88ba72e2cd6cfdcf5a5a"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"Validated dataset 2 using VirustTotal threshold 2","label":"val_dataset_t2.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634176,"persistentId":"","filename":"val_dataset_t2.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":17156686,"description":"Validated dataset 2 using VirustTotal threshold 2","storageIdentifier":"surf://store:19dbaecddff-de3968b47803","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"7e39c070b01be673e50901b0eb6ddc56468f101f"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"Validated dataset 3 using VirustTotal threshold 3","label":"val_dataset_t3.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634180,"persistentId":"","filename":"val_dataset_t3.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":14774825,"description":"Validated dataset 3 using VirustTotal threshold 3","storageIdentifier":"surf://store:19dbaecd6ac-ae65ce238d5b","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"ce50e2207a733b764377467c73eb368cecd4e217"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"Validated dataset 4 using VirustTotal threshold 4","label":"val_dataset_t4.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634179,"persistentId":"","filename":"val_dataset_t4.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":13382573,"description":"Validated dataset 4 using VirustTotal threshold 4","storageIdentifier":"surf://store:19dbaece3bd-3aa3da90e080","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8ebdb1be329bb17f8712af829dff51694135af86"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"Validated dataset 5 using VirustTotal threshold 5","label":"val_dataset_t5.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634177,"persistentId":"","filename":"val_dataset_t5.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":12393175,"description":"Validated dataset 5 using VirustTotal threshold 5","storageIdentifier":"surf://store:19dbaeccd9c-aae64000a678","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"e4dbf9f4420d30f7a7bc688bb349dac841800ba5"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}},{"description":"The parsing result of the VirusTotal reports. The datasets contain tens of features that can be used in future research.","label":"vt_lightweight.csv","restricted":false,"version":1,"datasetVersionId":34367,"dataFile":{"id":634173,"persistentId":"","filename":"vt_lightweight.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":923983450,"description":"The parsing result of the VirusTotal reports. The datasets contain tens of features that can be used in future research.","storageIdentifier":"surf://store:19dbae59634-709cc7692bae","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"81a4e8e094e2ce5381a13886710832a622e6b27a"},"tabularData":false,"creationDate":"2026-04-23","publicationDate":"2026-04-29","lastUpdateTime":"2026-04-29T08:31:50Z","fileAccessRequest":true}}]}}}