{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZFVLTXN7XWYTYVIAJLAKVQEOF","short_pith_number":"pith:KZFVLTXN","schema_version":"1.0","canonical_sha256":"564b55ceedfded89e2a802560556047169ca7589c39c3f6f94af771d4f0cdef8","source":{"kind":"arxiv","id":"2506.07308","version":2},"attestation_state":"computed","paper":{"title":"PASS: Private Attributes Protection with Stochastic Data Substitution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Fu (Richard) Chen, Hsiang Hsu, Shaohan Hu, Tarek Abdelzaher, Yizhuo Chen","submitted_at":"2025-06-08T22:48:07Z","abstract_excerpt":"The growing Machine Learning (ML) services require extensive collections of user data, which may inadvertently include people's private information irrelevant to the services. Various studies have been proposed to protect private attributes by removing them from the data while maintaining the utilities of the data for downstream tasks. Nevertheless, as we theoretically and empirically show in the paper, these methods reveal severe vulnerability because of a common weakness rooted in their adversarial training based strategies. To overcome this limitation, we propose a novel approach, PASS, des"},"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":"2506.07308","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T22:48:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"96e9a9c3f46cb807f73970bec79164078f6cfae20e4840836abc4d87e78628a4","abstract_canon_sha256":"55e75add8fd6fec22cb924ca9586996f9d1c34863d295f04cc19ed8c66e70d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:09.108700Z","signature_b64":"LcfWivEbXoZUmAQF4mf350/Ec87I0+2NtOu6SooYQ1CySVgHQNtzKWcCEdTVlrgjyFrBqu89nTf8F2EhFei7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"564b55ceedfded89e2a802560556047169ca7589c39c3f6f94af771d4f0cdef8","last_reissued_at":"2026-07-05T11:34:09.108240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:09.108240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PASS: Private Attributes Protection with Stochastic Data Substitution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Fu (Richard) Chen, Hsiang Hsu, Shaohan Hu, Tarek Abdelzaher, Yizhuo Chen","submitted_at":"2025-06-08T22:48:07Z","abstract_excerpt":"The growing Machine Learning (ML) services require extensive collections of user data, which may inadvertently include people's private information irrelevant to the services. Various studies have been proposed to protect private attributes by removing them from the data while maintaining the utilities of the data for downstream tasks. Nevertheless, as we theoretically and empirically show in the paper, these methods reveal severe vulnerability because of a common weakness rooted in their adversarial training based strategies. To overcome this limitation, we propose a novel approach, PASS, des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07308","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/2506.07308/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":"2506.07308","created_at":"2026-07-05T11:34:09.108296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07308v2","created_at":"2026-07-05T11:34:09.108296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07308","created_at":"2026-07-05T11:34:09.108296+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZFVLTXN7XWY","created_at":"2026-07-05T11:34:09.108296+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZFVLTXN7XWYTYVI","created_at":"2026-07-05T11:34:09.108296+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZFVLTXN","created_at":"2026-07-05T11:34:09.108296+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/KZFVLTXN7XWYTYVIAJLAKVQEOF","json":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF.json","graph_json":"https://pith.science/api/pith-number/KZFVLTXN7XWYTYVIAJLAKVQEOF/graph.json","events_json":"https://pith.science/api/pith-number/KZFVLTXN7XWYTYVIAJLAKVQEOF/events.json","paper":"https://pith.science/paper/KZFVLTXN"},"agent_actions":{"view_html":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF","download_json":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF.json","view_paper":"https://pith.science/paper/KZFVLTXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07308&json=true","fetch_graph":"https://pith.science/api/pith-number/KZFVLTXN7XWYTYVIAJLAKVQEOF/graph.json","fetch_events":"https://pith.science/api/pith-number/KZFVLTXN7XWYTYVIAJLAKVQEOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF/action/storage_attestation","attest_author":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF/action/author_attestation","sign_citation":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF/action/citation_signature","submit_replication":"https://pith.science/pith/KZFVLTXN7XWYTYVIAJLAKVQEOF/action/replication_record"}},"created_at":"2026-07-05T11:34:09.108296+00:00","updated_at":"2026-07-05T11:34:09.108296+00:00"}