{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TIUJRNDXEZGOKLWCCUUK7CPDNO","short_pith_number":"pith:TIUJRNDX","schema_version":"1.0","canonical_sha256":"9a2898b477264ce52ec21528af89e36bbe07994fbcd4fdf27acee566a10ace47","source":{"kind":"arxiv","id":"2309.01104","version":1},"attestation_state":"computed","paper":{"title":"Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Nicu Sebe, Weijie Wang, Zhengyu Zhao","submitted_at":"2023-09-03T07:01:34Z","abstract_excerpt":"Malicious use of deepfakes leads to serious public concerns and reduces people's trust in digital media. Although effective deepfake detectors have been proposed, they are substantially vulnerable to adversarial attacks. To evaluate the detector's robustness, recent studies have explored various attacks. However, all existing attacks are limited to 2D image perturbations, which are hard to translate into real-world facial changes. In this paper, we propose adversarial head turn (AdvHeat), the first attempt at 3D adversarial face views against deepfake detectors, based on face view synthesis fr"},"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":"2309.01104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-03T07:01:34Z","cross_cats_sorted":["cs.CR","cs.LG","cs.MM"],"title_canon_sha256":"84fbd76cc8b3b90d9b28ebcaebb97c811226ac97f1d747e6b3306f16c0d1ff1b","abstract_canon_sha256":"f18572d3b5cfed5e2ff48414752e64457cf763b8abbf3c2dc55cd323f105c59c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:32.378842Z","signature_b64":"yd/WqSXsev0eHnbzgopCX2T9JkOWm8lJ6IUeixbyq2LhCueBIklid6Dnd6f+w1ijlpdg0qP0KgSvw3yFpbMsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a2898b477264ce52ec21528af89e36bbe07994fbcd4fdf27acee566a10ace47","last_reissued_at":"2026-07-05T06:47:32.378265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:32.378265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bruno Lepri, Nicu Sebe, Weijie Wang, Zhengyu Zhao","submitted_at":"2023-09-03T07:01:34Z","abstract_excerpt":"Malicious use of deepfakes leads to serious public concerns and reduces people's trust in digital media. Although effective deepfake detectors have been proposed, they are substantially vulnerable to adversarial attacks. To evaluate the detector's robustness, recent studies have explored various attacks. However, all existing attacks are limited to 2D image perturbations, which are hard to translate into real-world facial changes. In this paper, we propose adversarial head turn (AdvHeat), the first attempt at 3D adversarial face views against deepfake detectors, based on face view synthesis fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01104","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/2309.01104/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":"2309.01104","created_at":"2026-07-05T06:47:32.378343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01104v1","created_at":"2026-07-05T06:47:32.378343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01104","created_at":"2026-07-05T06:47:32.378343+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIUJRNDXEZGO","created_at":"2026-07-05T06:47:32.378343+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIUJRNDXEZGOKLWC","created_at":"2026-07-05T06:47:32.378343+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIUJRNDX","created_at":"2026-07-05T06:47:32.378343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25544","citing_title":"Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12183","citing_title":"Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16540","citing_title":"PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO","json":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO.json","graph_json":"https://pith.science/api/pith-number/TIUJRNDXEZGOKLWCCUUK7CPDNO/graph.json","events_json":"https://pith.science/api/pith-number/TIUJRNDXEZGOKLWCCUUK7CPDNO/events.json","paper":"https://pith.science/paper/TIUJRNDX"},"agent_actions":{"view_html":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO","download_json":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO.json","view_paper":"https://pith.science/paper/TIUJRNDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01104&json=true","fetch_graph":"https://pith.science/api/pith-number/TIUJRNDXEZGOKLWCCUUK7CPDNO/graph.json","fetch_events":"https://pith.science/api/pith-number/TIUJRNDXEZGOKLWCCUUK7CPDNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO/action/storage_attestation","attest_author":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO/action/author_attestation","sign_citation":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO/action/citation_signature","submit_replication":"https://pith.science/pith/TIUJRNDXEZGOKLWCCUUK7CPDNO/action/replication_record"}},"created_at":"2026-07-05T06:47:32.378343+00:00","updated_at":"2026-07-05T06:47:32.378343+00:00"}