{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6NAJK6P5JTIFASPUAURY7EFTSH","short_pith_number":"pith:6NAJK6P5","schema_version":"1.0","canonical_sha256":"f3409579fd4cd05049f405238f90b391e97651d648506a6b76ed4c7b5261ddb0","source":{"kind":"arxiv","id":"1804.08757","version":3},"attestation_state":"computed","paper":{"title":"Siamese Generative Adversarial Privatizer for Biometric Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karol Piczak, Peter Kairouz, Ram Rajagopal, Tomasz Trzcinski, Witold Oleszkiewicz","submitted_at":"2018-04-23T21:57:28Z","abstract_excerpt":"State-of-the-art machine learning algorithms can be fooled by carefully crafted adversarial examples. As such, adversarial examples present a concrete problem in AI safety. In this work we turn the tables and ask the following question: can we harness the power of adversarial examples to prevent malicious adversaries from learning identifying information from data while allowing non-malicious entities to benefit from the utility of the same data? For instance, can we use adversarial examples to anonymize biometric dataset of faces while retaining usefulness of this data for other purposes, suc"},"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":"1804.08757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T21:57:28Z","cross_cats_sorted":[],"title_canon_sha256":"bbfa2079915390b1eae36c69628cb33ec1c356b53bcca1643eb9308b2116739f","abstract_canon_sha256":"e043e066ed0d80eb77c4d93031d7b028f250a6c8d2c5fa88eb195aba4b2f44ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:56.075731Z","signature_b64":"Uau+JyVK6fGWFbUJtbf7wkxqedcNIvLp9YdxrnfAx0masfqUWf/sN42CZKXak4soyzGCEyRowOGoefItpX5PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3409579fd4cd05049f405238f90b391e97651d648506a6b76ed4c7b5261ddb0","last_reissued_at":"2026-05-18T00:03:56.075053Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:56.075053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Siamese Generative Adversarial Privatizer for Biometric Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karol Piczak, Peter Kairouz, Ram Rajagopal, Tomasz Trzcinski, Witold Oleszkiewicz","submitted_at":"2018-04-23T21:57:28Z","abstract_excerpt":"State-of-the-art machine learning algorithms can be fooled by carefully crafted adversarial examples. As such, adversarial examples present a concrete problem in AI safety. In this work we turn the tables and ask the following question: can we harness the power of adversarial examples to prevent malicious adversaries from learning identifying information from data while allowing non-malicious entities to benefit from the utility of the same data? For instance, can we use adversarial examples to anonymize biometric dataset of faces while retaining usefulness of this data for other purposes, suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08757","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":"1804.08757","created_at":"2026-05-18T00:03:56.075151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08757v3","created_at":"2026-05-18T00:03:56.075151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08757","created_at":"2026-05-18T00:03:56.075151+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NAJK6P5JTIF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NAJK6P5JTIFASPU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NAJK6P5","created_at":"2026-05-18T12:32:11.075285+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/6NAJK6P5JTIFASPUAURY7EFTSH","json":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH.json","graph_json":"https://pith.science/api/pith-number/6NAJK6P5JTIFASPUAURY7EFTSH/graph.json","events_json":"https://pith.science/api/pith-number/6NAJK6P5JTIFASPUAURY7EFTSH/events.json","paper":"https://pith.science/paper/6NAJK6P5"},"agent_actions":{"view_html":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH","download_json":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH.json","view_paper":"https://pith.science/paper/6NAJK6P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08757&json=true","fetch_graph":"https://pith.science/api/pith-number/6NAJK6P5JTIFASPUAURY7EFTSH/graph.json","fetch_events":"https://pith.science/api/pith-number/6NAJK6P5JTIFASPUAURY7EFTSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH/action/storage_attestation","attest_author":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH/action/author_attestation","sign_citation":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH/action/citation_signature","submit_replication":"https://pith.science/pith/6NAJK6P5JTIFASPUAURY7EFTSH/action/replication_record"}},"created_at":"2026-05-18T00:03:56.075151+00:00","updated_at":"2026-05-18T00:03:56.075151+00:00"}