{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KQMMWQBSRTSBOGI7FUZ2KR7H7O","short_pith_number":"pith:KQMMWQBS","schema_version":"1.0","canonical_sha256":"5418cb40328ce417191f2d33a547e7fb805e81e76ddd9d859ed9cc9bafb6aa58","source":{"kind":"arxiv","id":"2410.06572","version":1},"attestation_state":"computed","paper":{"title":"Can DeepFake Speech be Reliably Detected?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SD","authors_text":"Arun Narayanan, Athula Balachandran, Hongbin Liu, Lun Wang, Pedro J. Moreno, Youzheng Chen","submitted_at":"2024-10-09T06:13:48Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like misinformation campaigns and fraud. While synthetic speech detectors (SSDs) exist to combat this, they are vulnerable to ``test domain shift\", exhibiting decreased performance when audio is altered through transcoding, playback, or background noise. This vulnerability is further exacerbated by deliberate manipulation of synthetic speech aimed at deceiving de"},"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":"2410.06572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T06:13:48Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"ddabb1d770df270fc6f0be822caad2153569e714b5a5f3139c09897dcf8bb47f","abstract_canon_sha256":"751f519f3a56b070d59813241663775375f9fe2d25b7a20f4f48e013acd72980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:04.285140Z","signature_b64":"sWlNnPRe302tI7GZvnTbziq44mB4O67oBUUL6VHVeAEEjjaqV1DiF1zsxuvAO39OYHeOOcOrJS1ibcH1IfzLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5418cb40328ce417191f2d33a547e7fb805e81e76ddd9d859ed9cc9bafb6aa58","last_reissued_at":"2026-07-05T09:18:04.284724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:04.284724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can DeepFake Speech be Reliably Detected?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SD","authors_text":"Arun Narayanan, Athula Balachandran, Hongbin Liu, Lun Wang, Pedro J. Moreno, Youzheng Chen","submitted_at":"2024-10-09T06:13:48Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like misinformation campaigns and fraud. While synthetic speech detectors (SSDs) exist to combat this, they are vulnerable to ``test domain shift\", exhibiting decreased performance when audio is altered through transcoding, playback, or background noise. This vulnerability is further exacerbated by deliberate manipulation of synthetic speech aimed at deceiving de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06572","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/2410.06572/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":"2410.06572","created_at":"2026-07-05T09:18:04.284783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06572v1","created_at":"2026-07-05T09:18:04.284783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06572","created_at":"2026-07-05T09:18:04.284783+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQMMWQBSRTSB","created_at":"2026-07-05T09:18:04.284783+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQMMWQBSRTSBOGI7","created_at":"2026-07-05T09:18:04.284783+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQMMWQBS","created_at":"2026-07-05T09:18:04.284783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06256","citing_title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O","json":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O.json","graph_json":"https://pith.science/api/pith-number/KQMMWQBSRTSBOGI7FUZ2KR7H7O/graph.json","events_json":"https://pith.science/api/pith-number/KQMMWQBSRTSBOGI7FUZ2KR7H7O/events.json","paper":"https://pith.science/paper/KQMMWQBS"},"agent_actions":{"view_html":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O","download_json":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O.json","view_paper":"https://pith.science/paper/KQMMWQBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06572&json=true","fetch_graph":"https://pith.science/api/pith-number/KQMMWQBSRTSBOGI7FUZ2KR7H7O/graph.json","fetch_events":"https://pith.science/api/pith-number/KQMMWQBSRTSBOGI7FUZ2KR7H7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O/action/storage_attestation","attest_author":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O/action/author_attestation","sign_citation":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O/action/citation_signature","submit_replication":"https://pith.science/pith/KQMMWQBSRTSBOGI7FUZ2KR7H7O/action/replication_record"}},"created_at":"2026-07-05T09:18:04.284783+00:00","updated_at":"2026-07-05T09:18:04.284783+00:00"}