{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ELZKTN4BHIMKJIZENNTETLLGHF","short_pith_number":"pith:ELZKTN4B","schema_version":"1.0","canonical_sha256":"22f2a9b7813a18a4a3246b6649ad663942d11fb146b62458e5bf0c1c2ea01556","source":{"kind":"arxiv","id":"2406.10932","version":3},"attestation_state":"computed","paper":{"title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jia Liu, Jiangkun Yang, Weiping Wen, Wenhan Yao, Yongqiang He","submitted_at":"2024-06-16T13:29:21Z","abstract_excerpt":"Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated, some security threats that make deep neural networks (DNNs) abnormal deserve to be researched. In recent years, the typical backdoor attacks have been researched in speech recognition systems. The existing backdoor methods are based on data poisoning. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, s"},"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":"2406.10932","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T13:29:21Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"0fda74d158941f253e8c45bdfe5bee7ec9e53a49a0fa741d01e1fcd4596d424e","abstract_canon_sha256":"36c4e0cb77fd0f9070a1e5bd2aa3bbda35b47c4d6f24e2eece69bc5cdbb14d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:19.485702Z","signature_b64":"HclMs+/Ldy7BFX1aLJ3kku9Raa3nGCPwI80hTU4KSnW6QSsZmsGHqYBs9fQxZD5Imh35TldcJCmLqw53feA+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22f2a9b7813a18a4a3246b6649ad663942d11fb146b62458e5bf0c1c2ea01556","last_reissued_at":"2026-07-05T09:22:19.485201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:19.485201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jia Liu, Jiangkun Yang, Weiping Wen, Wenhan Yao, Yongqiang He","submitted_at":"2024-06-16T13:29:21Z","abstract_excerpt":"Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated, some security threats that make deep neural networks (DNNs) abnormal deserve to be researched. In recent years, the typical backdoor attacks have been researched in speech recognition systems. The existing backdoor methods are based on data poisoning. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10932","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.10932/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":"2406.10932","created_at":"2026-07-05T09:22:19.485261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10932v3","created_at":"2026-07-05T09:22:19.485261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10932","created_at":"2026-07-05T09:22:19.485261+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELZKTN4BHIMK","created_at":"2026-07-05T09:22:19.485261+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELZKTN4BHIMKJIZE","created_at":"2026-07-05T09:22:19.485261+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELZKTN4B","created_at":"2026-07-05T09:22:19.485261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21052","citing_title":"Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF","json":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF.json","graph_json":"https://pith.science/api/pith-number/ELZKTN4BHIMKJIZENNTETLLGHF/graph.json","events_json":"https://pith.science/api/pith-number/ELZKTN4BHIMKJIZENNTETLLGHF/events.json","paper":"https://pith.science/paper/ELZKTN4B"},"agent_actions":{"view_html":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF","download_json":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF.json","view_paper":"https://pith.science/paper/ELZKTN4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10932&json=true","fetch_graph":"https://pith.science/api/pith-number/ELZKTN4BHIMKJIZENNTETLLGHF/graph.json","fetch_events":"https://pith.science/api/pith-number/ELZKTN4BHIMKJIZENNTETLLGHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF/action/storage_attestation","attest_author":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF/action/author_attestation","sign_citation":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF/action/citation_signature","submit_replication":"https://pith.science/pith/ELZKTN4BHIMKJIZENNTETLLGHF/action/replication_record"}},"created_at":"2026-07-05T09:22:19.485261+00:00","updated_at":"2026-07-05T09:22:19.485261+00:00"}