{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PKNC4N4YDF7EBINMQXBDF5XVU3","short_pith_number":"pith:PKNC4N4Y","schema_version":"1.0","canonical_sha256":"7a9a2e3798197e40a1ac85c232f6f5a6e0179e6b732a4bcc0e9314fe93771392","source":{"kind":"arxiv","id":"2505.18613","version":1},"attestation_state":"computed","paper":{"title":"MLRan: A Behavioural Dataset for Ransomware Analysis and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Adelodun Olaoluwa, Anca Delia Jurcut, Faithful Chiagoziem Onwuegbuche, Liliana Pasquale","submitted_at":"2025-05-24T09:22:53Z","abstract_excerpt":"Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this paper, we introduce MLRan, a behavioural ransomware dataset, comprising over 4,800 samples across 64 ransomware families and a balanced set of goodware samples. The samples span from 2006 to 2024 and encompass the four major types of ransomware: locker, crypto, ransomware-as-a-service, and modern variants. We also propose guidelines (GUIDE-MLRan), inspired by "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.18613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-24T09:22:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"98dc89ff1d078365d3bfc38d5e477f6dcf46410dcbda44ae280755e434b01a57","abstract_canon_sha256":"cbba21648eb22638e1e1160e10a9ba96bfbff267291c99644ffd4888b9967e6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.417223Z","signature_b64":"UB3VBV/JM4Yav7TrsBvHt6KO3TPIHfN7H8Bf0BdN7/BBbmlsaKQewrMLEeu+IFIK1S5qyeFQiBuI7l8UkXEyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a9a2e3798197e40a1ac85c232f6f5a6e0179e6b732a4bcc0e9314fe93771392","last_reissued_at":"2026-07-05T11:09:16.416781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.416781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLRan: A Behavioural Dataset for Ransomware Analysis and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Adelodun Olaoluwa, Anca Delia Jurcut, Faithful Chiagoziem Onwuegbuche, Liliana Pasquale","submitted_at":"2025-05-24T09:22:53Z","abstract_excerpt":"Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this paper, we introduce MLRan, a behavioural ransomware dataset, comprising over 4,800 samples across 64 ransomware families and a balanced set of goodware samples. The samples span from 2006 to 2024 and encompass the four major types of ransomware: locker, crypto, ransomware-as-a-service, and modern variants. We also propose guidelines (GUIDE-MLRan), inspired by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18613","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18613/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.18613","created_at":"2026-07-05T11:09:16.416838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18613v1","created_at":"2026-07-05T11:09:16.416838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18613","created_at":"2026-07-05T11:09:16.416838+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKNC4N4YDF7E","created_at":"2026-07-05T11:09:16.416838+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKNC4N4YDF7EBINM","created_at":"2026-07-05T11:09:16.416838+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKNC4N4Y","created_at":"2026-07-05T11:09:16.416838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3","json":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3.json","graph_json":"https://pith.science/api/pith-number/PKNC4N4YDF7EBINMQXBDF5XVU3/graph.json","events_json":"https://pith.science/api/pith-number/PKNC4N4YDF7EBINMQXBDF5XVU3/events.json","paper":"https://pith.science/paper/PKNC4N4Y"},"agent_actions":{"view_html":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3","download_json":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3.json","view_paper":"https://pith.science/paper/PKNC4N4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18613&json=true","fetch_graph":"https://pith.science/api/pith-number/PKNC4N4YDF7EBINMQXBDF5XVU3/graph.json","fetch_events":"https://pith.science/api/pith-number/PKNC4N4YDF7EBINMQXBDF5XVU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3/action/storage_attestation","attest_author":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3/action/author_attestation","sign_citation":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3/action/citation_signature","submit_replication":"https://pith.science/pith/PKNC4N4YDF7EBINMQXBDF5XVU3/action/replication_record"}},"created_at":"2026-07-05T11:09:16.416838+00:00","updated_at":"2026-07-05T11:09:16.416838+00:00"}