{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BMAK3MPYZGAJDQH6UYRMTM3UJB","short_pith_number":"pith:BMAK3MPY","schema_version":"1.0","canonical_sha256":"0b00adb1f8c98091c0fea622c9b374486cc55f0d453fc0a118d6ea30b4c53b50","source":{"kind":"arxiv","id":"2402.19232","version":2},"attestation_state":"computed","paper":{"title":"Trained Random Forests Completely Reveal your Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Julien Ferry, Ricardo Fukasawa, Thibaut Vidal, Timoth\\'ee Pascal","submitted_at":"2024-02-29T15:05:59Z","abstract_excerpt":"We introduce an optimization-based reconstruction attack capable of completely or near-completely reconstructing a dataset utilized for training a random forest. Notably, our approach relies solely on information readily available in commonly used libraries such as scikit-learn. To achieve this, we formulate the reconstruction problem as a combinatorial problem under a maximum likelihood objective. We demonstrate that this problem is NP-hard, though solvable at scale using constraint programming -- an approach rooted in constraint propagation and solution-domain reduction. Through an extensive"},"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":"2402.19232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T15:05:59Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"26bd696a791333a491c68597f7743054a2b00bf1eb9d24110c06ff1a7b2a7c3b","abstract_canon_sha256":"bab8c1d7987118e23abb218cb17e0d99f3ac8e4dd3a205c390db24579813a8b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:33.908923Z","signature_b64":"u4dht4reKthUwdVyfMDuGb0ac/GjG3JJse210LoyncJT/ACFEQ/+B4y1OHrcpMYirbi97Bgh7VymnJbqqYL0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b00adb1f8c98091c0fea622c9b374486cc55f0d453fc0a118d6ea30b4c53b50","last_reissued_at":"2026-07-05T08:55:33.908492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:33.908492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trained Random Forests Completely Reveal your Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Julien Ferry, Ricardo Fukasawa, Thibaut Vidal, Timoth\\'ee Pascal","submitted_at":"2024-02-29T15:05:59Z","abstract_excerpt":"We introduce an optimization-based reconstruction attack capable of completely or near-completely reconstructing a dataset utilized for training a random forest. Notably, our approach relies solely on information readily available in commonly used libraries such as scikit-learn. To achieve this, we formulate the reconstruction problem as a combinatorial problem under a maximum likelihood objective. We demonstrate that this problem is NP-hard, though solvable at scale using constraint programming -- an approach rooted in constraint propagation and solution-domain reduction. Through an extensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19232","kind":"arxiv","version":2},"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/2402.19232/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":"2402.19232","created_at":"2026-07-05T08:55:33.908552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19232v2","created_at":"2026-07-05T08:55:33.908552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19232","created_at":"2026-07-05T08:55:33.908552+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMAK3MPYZGAJ","created_at":"2026-07-05T08:55:33.908552+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMAK3MPYZGAJDQH6","created_at":"2026-07-05T08:55:33.908552+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMAK3MPY","created_at":"2026-07-05T08:55:33.908552+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/BMAK3MPYZGAJDQH6UYRMTM3UJB","json":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB.json","graph_json":"https://pith.science/api/pith-number/BMAK3MPYZGAJDQH6UYRMTM3UJB/graph.json","events_json":"https://pith.science/api/pith-number/BMAK3MPYZGAJDQH6UYRMTM3UJB/events.json","paper":"https://pith.science/paper/BMAK3MPY"},"agent_actions":{"view_html":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB","download_json":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB.json","view_paper":"https://pith.science/paper/BMAK3MPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19232&json=true","fetch_graph":"https://pith.science/api/pith-number/BMAK3MPYZGAJDQH6UYRMTM3UJB/graph.json","fetch_events":"https://pith.science/api/pith-number/BMAK3MPYZGAJDQH6UYRMTM3UJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB/action/storage_attestation","attest_author":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB/action/author_attestation","sign_citation":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB/action/citation_signature","submit_replication":"https://pith.science/pith/BMAK3MPYZGAJDQH6UYRMTM3UJB/action/replication_record"}},"created_at":"2026-07-05T08:55:33.908552+00:00","updated_at":"2026-07-05T08:55:33.908552+00:00"}