{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PLCQPPTHCTXIMWZU2MKIBBFGSW","short_pith_number":"pith:PLCQPPTH","schema_version":"1.0","canonical_sha256":"7ac507be6714ee865b34d3148084a695a915d248c9bbb79dbbc0caacee50e106","source":{"kind":"arxiv","id":"1809.06546","version":3},"attestation_state":"computed","paper":{"title":"Model-Protected Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Changshui Zhang, Fei Wang, Jian Liang, Jiayu Zhou, Xiaoqian Jiang, Ziqi Liu","submitted_at":"2018-09-18T06:16:38Z","abstract_excerpt":"Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithms can ``leak\" information from different models across different tasks, MTL poses a potential security risk. Specifically, an adversary may participate in the MTL process through one task and thereby acquire the model information for another task. The previously proposed privacy-"},"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":"1809.06546","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-18T06:16:38Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"15f266c7f50ed33781be573ed50dc80466d93a7bebeac497dd05a9b8be00e1aa","abstract_canon_sha256":"051a47830e09f6cc02c8ef341b6ad714368cacd3adeee75ab401b9ac8140530f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:45.971563Z","signature_b64":"KAvzuRNACI+Nb0qgxF/AWJT6Bcr+eqTbmHA8/4cozQ5+3JLKi74FJSOHtPHCpIIzwrTVVgxthF56VXDhNzvHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ac507be6714ee865b34d3148084a695a915d248c9bbb79dbbc0caacee50e106","last_reissued_at":"2026-05-17T23:41:45.971016Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:45.971016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Protected Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Changshui Zhang, Fei Wang, Jian Liang, Jiayu Zhou, Xiaoqian Jiang, Ziqi Liu","submitted_at":"2018-09-18T06:16:38Z","abstract_excerpt":"Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithms can ``leak\" information from different models across different tasks, MTL poses a potential security risk. Specifically, an adversary may participate in the MTL process through one task and thereby acquire the model information for another task. The previously proposed privacy-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06546","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.06546","created_at":"2026-05-17T23:41:45.971102+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06546v3","created_at":"2026-05-17T23:41:45.971102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06546","created_at":"2026-05-17T23:41:45.971102+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLCQPPTHCTXI","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLCQPPTHCTXIMWZU","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLCQPPTH","created_at":"2026-05-18T12:32:46.962924+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/PLCQPPTHCTXIMWZU2MKIBBFGSW","json":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW.json","graph_json":"https://pith.science/api/pith-number/PLCQPPTHCTXIMWZU2MKIBBFGSW/graph.json","events_json":"https://pith.science/api/pith-number/PLCQPPTHCTXIMWZU2MKIBBFGSW/events.json","paper":"https://pith.science/paper/PLCQPPTH"},"agent_actions":{"view_html":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW","download_json":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW.json","view_paper":"https://pith.science/paper/PLCQPPTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06546&json=true","fetch_graph":"https://pith.science/api/pith-number/PLCQPPTHCTXIMWZU2MKIBBFGSW/graph.json","fetch_events":"https://pith.science/api/pith-number/PLCQPPTHCTXIMWZU2MKIBBFGSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW/action/storage_attestation","attest_author":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW/action/author_attestation","sign_citation":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW/action/citation_signature","submit_replication":"https://pith.science/pith/PLCQPPTHCTXIMWZU2MKIBBFGSW/action/replication_record"}},"created_at":"2026-05-17T23:41:45.971102+00:00","updated_at":"2026-05-17T23:41:45.971102+00:00"}