{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PFL75OCSVMNM5QPY7BIQAFNVNY","short_pith_number":"pith:PFL75OCS","schema_version":"1.0","canonical_sha256":"7957feb852ab1acec1f8f8510015b56e043054d419394d441e505a85b05049f6","source":{"kind":"arxiv","id":"2607.00899","version":1},"attestation_state":"computed","paper":{"title":"Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hao Ma, Massimiliano Todisco, Michele Panariello, Nicholas Evan, Sizhou Chen, Xiao-Lei Zhang, Xuelong Li, Yibo Bai","submitted_at":"2026-07-01T13:02:29Z","abstract_excerpt":"Modern automatic speaker verification (ASV) systems are vulnerable to adversarial perturbations. Diffusion-based purification has recently shown strong effectiveness against such perturbations, but its reverse denoising process requires iterative sampling and leads to high inference latency. We find that the forward noising process provides most of the robustness gain. Motivated by this observation, we reformulate adversarial purification as a learnable noising problem, and propose the Positive-Incentive Noise Predictor (PnP), the first framework that explicitly introduces positive-incentive n"},"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":"2607.00899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-01T13:02:29Z","cross_cats_sorted":[],"title_canon_sha256":"1fff6ad1ce5bafea88036691361a4ff1aa19eb70398711082d2c05801baba8a8","abstract_canon_sha256":"6b2fe5c3c77a2c63cc31c0abe9423b723226fb4877bc5d7ab302ae53059fa0e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:22.861039Z","signature_b64":"yLO3aEHw8e3foFHAb4LmvpQ96II4sf1X1QxAglPuAFSygAEX6/jYTop1NBpNgJMIfPG95HA6+RPIrbcQSXJgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7957feb852ab1acec1f8f8510015b56e043054d419394d441e505a85b05049f6","last_reissued_at":"2026-07-02T01:18:22.860641Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:22.860641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hao Ma, Massimiliano Todisco, Michele Panariello, Nicholas Evan, Sizhou Chen, Xiao-Lei Zhang, Xuelong Li, Yibo Bai","submitted_at":"2026-07-01T13:02:29Z","abstract_excerpt":"Modern automatic speaker verification (ASV) systems are vulnerable to adversarial perturbations. Diffusion-based purification has recently shown strong effectiveness against such perturbations, but its reverse denoising process requires iterative sampling and leads to high inference latency. We find that the forward noising process provides most of the robustness gain. Motivated by this observation, we reformulate adversarial purification as a learnable noising problem, and propose the Positive-Incentive Noise Predictor (PnP), the first framework that explicitly introduces positive-incentive n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00899","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/2607.00899/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":"2607.00899","created_at":"2026-07-02T01:18:22.860704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00899v1","created_at":"2026-07-02T01:18:22.860704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00899","created_at":"2026-07-02T01:18:22.860704+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFL75OCSVMNM","created_at":"2026-07-02T01:18:22.860704+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFL75OCSVMNM5QPY","created_at":"2026-07-02T01:18:22.860704+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFL75OCS","created_at":"2026-07-02T01:18:22.860704+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/PFL75OCSVMNM5QPY7BIQAFNVNY","json":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY.json","graph_json":"https://pith.science/api/pith-number/PFL75OCSVMNM5QPY7BIQAFNVNY/graph.json","events_json":"https://pith.science/api/pith-number/PFL75OCSVMNM5QPY7BIQAFNVNY/events.json","paper":"https://pith.science/paper/PFL75OCS"},"agent_actions":{"view_html":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY","download_json":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY.json","view_paper":"https://pith.science/paper/PFL75OCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00899&json=true","fetch_graph":"https://pith.science/api/pith-number/PFL75OCSVMNM5QPY7BIQAFNVNY/graph.json","fetch_events":"https://pith.science/api/pith-number/PFL75OCSVMNM5QPY7BIQAFNVNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY/action/storage_attestation","attest_author":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY/action/author_attestation","sign_citation":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY/action/citation_signature","submit_replication":"https://pith.science/pith/PFL75OCSVMNM5QPY7BIQAFNVNY/action/replication_record"}},"created_at":"2026-07-02T01:18:22.860704+00:00","updated_at":"2026-07-02T01:18:22.860704+00:00"}