{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQFILTNT7WNPGOFBAVY7ENEVFZ","short_pith_number":"pith:ZQFILTNT","schema_version":"1.0","canonical_sha256":"cc0a85cdb3fd9af338a10571f234952e6e4ff2fe36f0127653ee7ccb03b507ef","source":{"kind":"arxiv","id":"2506.12344","version":1},"attestation_state":"computed","paper":{"title":"Restoring Gaussian Blurred Face Images for Deanonymization Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Gang Wang, Haoyu Zhai, Pirouz Naghavi, Qingying Hao, Shuo Wang","submitted_at":"2025-06-14T04:41:05Z","abstract_excerpt":"Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this question by developing a deblurring method called Revelio. The key intuition is to leverage a generative model's memorization effect and approximate the inverse function of Gaussian blur for face restoration. Compared with existing methods, we design the deblurring process to be identity-preserving. It "},"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":"2506.12344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-14T04:41:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3e27b84cb430825d00c2d2235659a291889e202e4ede96635e412a2fdb80a4e","abstract_canon_sha256":"6301d3c45b67931f8ee5bf174dca83961b62f542efb1d3fa29ab49018c32dabd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:51.610263Z","signature_b64":"vR7Ywv5vXhMoQT6V1Okj1OXmOM5WLxQTmT8vvqyhqDNVh63QsKEMUP7el3ZFh8a0yAShhNBOIEseC9OITCl7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc0a85cdb3fd9af338a10571f234952e6e4ff2fe36f0127653ee7ccb03b507ef","last_reissued_at":"2026-07-05T11:21:51.609806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:51.609806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Restoring Gaussian Blurred Face Images for Deanonymization Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Gang Wang, Haoyu Zhai, Pirouz Naghavi, Qingying Hao, Shuo Wang","submitted_at":"2025-06-14T04:41:05Z","abstract_excerpt":"Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this question by developing a deblurring method called Revelio. The key intuition is to leverage a generative model's memorization effect and approximate the inverse function of Gaussian blur for face restoration. Compared with existing methods, we design the deblurring process to be identity-preserving. It "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12344","kind":"arxiv","version":1},"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/2506.12344/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":"2506.12344","created_at":"2026-07-05T11:21:51.609864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12344v1","created_at":"2026-07-05T11:21:51.609864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12344","created_at":"2026-07-05T11:21:51.609864+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQFILTNT7WNP","created_at":"2026-07-05T11:21:51.609864+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQFILTNT7WNPGOFB","created_at":"2026-07-05T11:21:51.609864+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQFILTNT","created_at":"2026-07-05T11:21:51.609864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.27817","citing_title":"Towards Context-Aware Image Anonymization with Multi-Agent Reasoning","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ","json":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ.json","graph_json":"https://pith.science/api/pith-number/ZQFILTNT7WNPGOFBAVY7ENEVFZ/graph.json","events_json":"https://pith.science/api/pith-number/ZQFILTNT7WNPGOFBAVY7ENEVFZ/events.json","paper":"https://pith.science/paper/ZQFILTNT"},"agent_actions":{"view_html":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ","download_json":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ.json","view_paper":"https://pith.science/paper/ZQFILTNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12344&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQFILTNT7WNPGOFBAVY7ENEVFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQFILTNT7WNPGOFBAVY7ENEVFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZQFILTNT7WNPGOFBAVY7ENEVFZ/action/replication_record"}},"created_at":"2026-07-05T11:21:51.609864+00:00","updated_at":"2026-07-05T11:21:51.609864+00:00"}