{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZF3MI5YAQK6AVRKEI57EAKENO","short_pith_number":"pith:EZF3MI5Y","schema_version":"1.0","canonical_sha256":"264bb623b80415e0562a223bf201446bb0ba4bb913d19bbafcf2f7484ec14548","source":{"kind":"arxiv","id":"2606.20893","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SD","authors_text":"Ajita Rattani, Bharath Krishnamurthy, Sameek Bhattacharya","submitted_at":"2026-06-18T19:40:46Z","abstract_excerpt":"Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradient descent (PGD) and Carlini-Wagner, require costly iterative updates in the high-dimensional waveform domain. Generative attacks allow single-shot synthesis but often introduce perceptible artifacts or depend on computationally intensive architectures, while diffusion and autoregressive approaches incur high inference latency. To address this gap, we"},"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":"2606.20893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T19:40:46Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"fb2b87236e653947d1f4eebd8c7dd115c149d01411002de3adf80d1b3c2cec74","abstract_canon_sha256":"abab53358db800a0b8c097e35a697c1d9a86f0094f4c1170b47545037c725ebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:12:02.007293Z","signature_b64":"KpicV5XUVBN5MOntVezj9Chd7KX/qJ+fHswJcfJptGMJdqAmr2Cbr8fBL1vfrE9yOI/qkccnlvf0/jdNHeTZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"264bb623b80415e0562a223bf201446bb0ba4bb913d19bbafcf2f7484ec14548","last_reissued_at":"2026-06-23T00:12:02.006815Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:12:02.006815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SD","authors_text":"Ajita Rattani, Bharath Krishnamurthy, Sameek Bhattacharya","submitted_at":"2026-06-18T19:40:46Z","abstract_excerpt":"Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradient descent (PGD) and Carlini-Wagner, require costly iterative updates in the high-dimensional waveform domain. Generative attacks allow single-shot synthesis but often introduce perceptible artifacts or depend on computationally intensive architectures, while diffusion and autoregressive approaches incur high inference latency. To address this gap, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20893","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/2606.20893/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":"2606.20893","created_at":"2026-06-23T00:12:02.006872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20893v1","created_at":"2026-06-23T00:12:02.006872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20893","created_at":"2026-06-23T00:12:02.006872+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZF3MI5YAQK6","created_at":"2026-06-23T00:12:02.006872+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZF3MI5YAQK6AVRK","created_at":"2026-06-23T00:12:02.006872+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZF3MI5Y","created_at":"2026-06-23T00:12:02.006872+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/EZF3MI5YAQK6AVRKEI57EAKENO","json":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO.json","graph_json":"https://pith.science/api/pith-number/EZF3MI5YAQK6AVRKEI57EAKENO/graph.json","events_json":"https://pith.science/api/pith-number/EZF3MI5YAQK6AVRKEI57EAKENO/events.json","paper":"https://pith.science/paper/EZF3MI5Y"},"agent_actions":{"view_html":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO","download_json":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO.json","view_paper":"https://pith.science/paper/EZF3MI5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20893&json=true","fetch_graph":"https://pith.science/api/pith-number/EZF3MI5YAQK6AVRKEI57EAKENO/graph.json","fetch_events":"https://pith.science/api/pith-number/EZF3MI5YAQK6AVRKEI57EAKENO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO/action/storage_attestation","attest_author":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO/action/author_attestation","sign_citation":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO/action/citation_signature","submit_replication":"https://pith.science/pith/EZF3MI5YAQK6AVRKEI57EAKENO/action/replication_record"}},"created_at":"2026-06-23T00:12:02.006872+00:00","updated_at":"2026-06-23T00:12:02.006872+00:00"}