{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RYWYL6HRGN3K5W47L2Y7G55HWQ","short_pith_number":"pith:RYWYL6HR","schema_version":"1.0","canonical_sha256":"8e2d85f8f13376aedb9f5eb1f377a7b436a463fd91dc09f6148223011df3fc3c","source":{"kind":"arxiv","id":"2606.21052","version":1},"attestation_state":"computed","paper":{"title":"Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SD","authors_text":"Jia Zhang, Xihao Xie, Yongbin Huang","submitted_at":"2026-06-19T02:36:11Z","abstract_excerpt":"Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demonstrate that SER models can be reliably compromised with hi"},"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":"2606.21052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-19T02:36:11Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"50df481d19bcf1b8588349a8118f168e5192bfe3bfa6114f45ae7b027e4ed15c","abstract_canon_sha256":"a346aa74935faca60fc1fadfb75b6ffc40a78f49fd76da1bf0facbfaf4153393"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:28.321600Z","signature_b64":"SniZiFUc+oToLhQFpKAUve+BzbDQFjjRrpcXd1K4UAG8Y3+MRt5ItNq7dTfcbTVf1WqNl0i9oTkNaC9F4Z5ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2d85f8f13376aedb9f5eb1f377a7b436a463fd91dc09f6148223011df3fc3c","last_reissued_at":"2026-06-23T01:12:28.321114Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:28.321114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SD","authors_text":"Jia Zhang, Xihao Xie, Yongbin Huang","submitted_at":"2026-06-19T02:36:11Z","abstract_excerpt":"Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demonstrate that SER models can be reliably compromised with hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21052","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/2606.21052/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":"2606.21052","created_at":"2026-06-23T01:12:28.321177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21052v1","created_at":"2026-06-23T01:12:28.321177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21052","created_at":"2026-06-23T01:12:28.321177+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYWYL6HRGN3K","created_at":"2026-06-23T01:12:28.321177+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYWYL6HRGN3K5W47","created_at":"2026-06-23T01:12:28.321177+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYWYL6HR","created_at":"2026-06-23T01:12:28.321177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ","json":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ.json","graph_json":"https://pith.science/api/pith-number/RYWYL6HRGN3K5W47L2Y7G55HWQ/graph.json","events_json":"https://pith.science/api/pith-number/RYWYL6HRGN3K5W47L2Y7G55HWQ/events.json","paper":"https://pith.science/paper/RYWYL6HR"},"agent_actions":{"view_html":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ","download_json":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ.json","view_paper":"https://pith.science/paper/RYWYL6HR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21052&json=true","fetch_graph":"https://pith.science/api/pith-number/RYWYL6HRGN3K5W47L2Y7G55HWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RYWYL6HRGN3K5W47L2Y7G55HWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ/action/storage_attestation","attest_author":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ/action/author_attestation","sign_citation":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ/action/citation_signature","submit_replication":"https://pith.science/pith/RYWYL6HRGN3K5W47L2Y7G55HWQ/action/replication_record"}},"created_at":"2026-06-23T01:12:28.321177+00:00","updated_at":"2026-06-23T01:12:28.321177+00:00"}