{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZVDS3Y4FMP5DO2F4IHXFTNITUY","short_pith_number":"pith:ZVDS3Y4F","schema_version":"1.0","canonical_sha256":"cd472de38563fa3768bc41ee59b513a60a0e40efe76c1587969483668f7e1b39","source":{"kind":"arxiv","id":"1609.00408","version":2},"attestation_state":"computed","paper":{"title":"Defeating Image Obfuscation with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Reza Shokri, Richard McPherson, Vitaly Shmatikov","submitted_at":"2016-09-01T21:38:15Z","abstract_excerpt":"We demonstrate that modern image recognition methods based on artificial neural networks can recover hidden information from images protected by various forms of obfuscation. The obfuscation techniques considered in this paper are mosaicing (also known as pixelation), blurring (as used by YouTube), and P3, a recently proposed system for privacy-preserving photo sharing that encrypts the significant JPEG coefficients to make images unrecognizable by humans. We empirically show how to train artificial neural networks to successfully identify faces and recognize objects and handwritten digits eve"},"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":"1609.00408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2016-09-01T21:38:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3cbc90a1eb23220521cbe69513934763233bc4c1092e8506fef8942f414543ab","abstract_canon_sha256":"bc0ad6d92ea18773efc82a989a2f0393046d4f7633c5a77f5d4eb0e248a5a9a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:05:10.291211Z","signature_b64":"T9YiGVJEtA1T2aiyICZWa9KGw9sGQvk9wyBgvnI9P3Bk5Gr8y4ilSDAp6tSgoeRXTp1QQz2JiL2yce9+CYtgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd472de38563fa3768bc41ee59b513a60a0e40efe76c1587969483668f7e1b39","last_reissued_at":"2026-05-18T01:05:10.290574Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:05:10.290574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defeating Image Obfuscation with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Reza Shokri, Richard McPherson, Vitaly Shmatikov","submitted_at":"2016-09-01T21:38:15Z","abstract_excerpt":"We demonstrate that modern image recognition methods based on artificial neural networks can recover hidden information from images protected by various forms of obfuscation. The obfuscation techniques considered in this paper are mosaicing (also known as pixelation), blurring (as used by YouTube), and P3, a recently proposed system for privacy-preserving photo sharing that encrypts the significant JPEG coefficients to make images unrecognizable by humans. We empirically show how to train artificial neural networks to successfully identify faces and recognize objects and handwritten digits eve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.00408","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":""},"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":"1609.00408","created_at":"2026-05-18T01:05:10.290681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.00408v2","created_at":"2026-05-18T01:05:10.290681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.00408","created_at":"2026-05-18T01:05:10.290681+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVDS3Y4FMP5D","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVDS3Y4FMP5DO2F4","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVDS3Y4F","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.11979","citing_title":"A Utility-Preserving GAN for Face Obscuration","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.17185","citing_title":"A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12068","citing_title":"Privacy-Preserving Structureless Visual Localization via Image Obfuscation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17163","citing_title":"PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY","json":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY.json","graph_json":"https://pith.science/api/pith-number/ZVDS3Y4FMP5DO2F4IHXFTNITUY/graph.json","events_json":"https://pith.science/api/pith-number/ZVDS3Y4FMP5DO2F4IHXFTNITUY/events.json","paper":"https://pith.science/paper/ZVDS3Y4F"},"agent_actions":{"view_html":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY","download_json":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY.json","view_paper":"https://pith.science/paper/ZVDS3Y4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.00408&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVDS3Y4FMP5DO2F4IHXFTNITUY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVDS3Y4FMP5DO2F4IHXFTNITUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY/action/storage_attestation","attest_author":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY/action/author_attestation","sign_citation":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY/action/citation_signature","submit_replication":"https://pith.science/pith/ZVDS3Y4FMP5DO2F4IHXFTNITUY/action/replication_record"}},"created_at":"2026-05-18T01:05:10.290681+00:00","updated_at":"2026-05-18T01:05:10.290681+00:00"}