{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DQCJE6P7EQ35BC3VI7KUJ3V5BD","short_pith_number":"pith:DQCJE6P7","schema_version":"1.0","canonical_sha256":"1c049279ff2437d08b7547d544eebd08e739ea250236f7b97c4c405c59c67907","source":{"kind":"arxiv","id":"1807.08379","version":2},"attestation_state":"computed","paper":{"title":"Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Jin, Zhangyang Wang, Zhaowen Wang, Zhenyu Wu","submitted_at":"2018-07-22T22:30:56Z","abstract_excerpt":"This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation transform for the original video inputs, in order to optimize the trade-off between target task performance and the associated privacy budgets on the degraded video. A notable challenge is that the privacy budget, often defined and measured in task-driven contexts, cannot be reliably indicated using any single model performance, because a strong protection o"},"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":"1807.08379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-22T22:30:56Z","cross_cats_sorted":[],"title_canon_sha256":"90da5539ca3ee4d882c856a669f427a823ad61d8aa411d9913323af45083a667","abstract_canon_sha256":"22b276928674d7dacc7836c720f5e5574f106eee5a704c1859e9dfebdcf52358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:23.045343Z","signature_b64":"4pOvsDjjQvm/fgxrvfTJtO2FbEVVACLH72+CqaFmjJ+jGTvCNDxsgTkXNKxefIYN7PcpoSnEh2z+UxAhZvZMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c049279ff2437d08b7547d544eebd08e739ea250236f7b97c4c405c59c67907","last_reissued_at":"2026-07-05T01:45:23.044981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:23.044981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Jin, Zhangyang Wang, Zhaowen Wang, Zhenyu Wu","submitted_at":"2018-07-22T22:30:56Z","abstract_excerpt":"This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation transform for the original video inputs, in order to optimize the trade-off between target task performance and the associated privacy budgets on the degraded video. A notable challenge is that the privacy budget, often defined and measured in task-driven contexts, cannot be reliably indicated using any single model performance, because a strong protection o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08379","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/1807.08379/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":"1807.08379","created_at":"2026-07-05T01:45:23.045043+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08379v2","created_at":"2026-07-05T01:45:23.045043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08379","created_at":"2026-07-05T01:45:23.045043+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQCJE6P7EQ35","created_at":"2026-07-05T01:45:23.045043+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQCJE6P7EQ35BC3V","created_at":"2026-07-05T01:45:23.045043+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQCJE6P7","created_at":"2026-07-05T01:45:23.045043+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/DQCJE6P7EQ35BC3VI7KUJ3V5BD","json":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD.json","graph_json":"https://pith.science/api/pith-number/DQCJE6P7EQ35BC3VI7KUJ3V5BD/graph.json","events_json":"https://pith.science/api/pith-number/DQCJE6P7EQ35BC3VI7KUJ3V5BD/events.json","paper":"https://pith.science/paper/DQCJE6P7"},"agent_actions":{"view_html":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD","download_json":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD.json","view_paper":"https://pith.science/paper/DQCJE6P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08379&json=true","fetch_graph":"https://pith.science/api/pith-number/DQCJE6P7EQ35BC3VI7KUJ3V5BD/graph.json","fetch_events":"https://pith.science/api/pith-number/DQCJE6P7EQ35BC3VI7KUJ3V5BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD/action/storage_attestation","attest_author":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD/action/author_attestation","sign_citation":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD/action/citation_signature","submit_replication":"https://pith.science/pith/DQCJE6P7EQ35BC3VI7KUJ3V5BD/action/replication_record"}},"created_at":"2026-07-05T01:45:23.045043+00:00","updated_at":"2026-07-05T01:45:23.045043+00:00"}