{"as_of":"2026-08-08T13:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d28f594d8af48c3109022019243159c1cdbe83b5703433b4ea4b4ef0cd259a6b","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:27:38.554271Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.09296/citation-record","integrity":"/paper/2509.09296/integrity","json":"/paper/2509.09296/citation-record.json","paper":"/paper/2509.09296"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.435208Z","title":"Speaker Recognition Based on Deep Learning: An Overview,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.435208Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:723f511d59be1cc98e1524588c9157f09f6eb27307974966d3157634812ea9fe","observation_id":"d39a6b6c-8325-4fae-b7b7-bd1699440c3e","resolution":{"observed_at":"2026-08-04T19:27:38.435208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.439108Z","title":"Adversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.439108Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:e058e0a82cdd2a327432a7444197682f62ea15c779f7cf29527f642e06b78dcc","observation_id":"6209c17b-9bb0-43d2-afd2-2c71841cb5c2","resolution":{"observed_at":"2026-08-04T19:27:38.439108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.14970","last_updated":"2023-08-29T01:50:01Z","snapshot_observed_at":"2026-07-06T16:11:31.948429Z","submitted_at":"2023-08-29T01:50:01Z","title":"Audio Deepfake Detection: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.14970","snapshot_observed_at":"2026-08-04T19:27:38.442513Z","title":"Audio Deepfake Detection: A Survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.442513Z"},"links":{"cited_paper":"/paper/2308.14970","citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:b69810080a84b3199127f4d00b80c193b3f4f5bab520fb362062bafaac22a9c0","observation_id":"4ddc6da2-b4ad-420d-8748-e9172fd96a2f","resolution":{"observed_at":"2026-08-04T19:27:38.442513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.446413Z","title":"Black-box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Exam- ples","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.446413Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:f1246d78399233f01558cc71e47af17c5df6beaf7c71c5cd301fe70051ef826d","observation_id":"50792f64-08d2-4e22-ac31-601c284a24e3","resolution":{"observed_at":"2026-08-04T19:27:38.446413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.449714Z","title":"AdvSV: An Over-the-air Adversarial Attack Dataset for Speaker Verification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.449714Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:15062281519a1005ec98959d99e14357db454dc15cb401f0c69cbc981309e8db","observation_id":"62e1a2a6-306b-4543-8281-842b1e918483","resolution":{"observed_at":"2026-08-04T19:27:38.449714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.452859Z","title":"An Initial Investigation of Neural Replay Simulator for Over-the-air Adversarial Perturbations to Automatic Speaker Verification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.452859Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:c4035fd2387b67ed6a6313654429138ad2d0db44e2b5594f88f6d563e571bf99","observation_id":"f8a32f76-b91c-415f-81eb-df3c6c04a195","resolution":{"observed_at":"2026-08-04T19:27:38.452859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.456189Z","title":"The Defender’s Perspective on Automatic Speaker Verification: An Overview,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.456189Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:7b8fe84209ed9df1e2c4adecf58d17c48e631e88077a0098ce2d5062fd49cbe3","observation_id":"1af80839-8663-4ac7-b15a-9eb00a61a3a0","resolution":{"observed_at":"2026-08-04T19:27:38.456189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.458886Z","title":"Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.458886Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:f7657d91533b87013ff094963fa1d5ccf755f366b9c696a39f998e11ceccc7fc","observation_id":"64132742-51fb-4480-a73d-4a64d902da11","resolution":{"observed_at":"2026-08-04T19:27:38.458886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.461956Z","title":"Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.461956Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:0444a788eab668bd2279dcd2de8dabfd3cb8a17ada743b831403a00d8a800f5c","observation_id":"6f88b312-a6aa-4feb-873b-6c44e19a9127","resolution":{"observed_at":"2026-08-04T19:27:38.461956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.464766Z","title":"In- vestigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.464766Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:79bdb2c36d3bed68c6d5ff5d2af3f178c85765bd53d8cc759a2e67a5716782dc","observation_id":"010ada75-aeb6-4214-a01c-d1eb211480e9","resolution":{"observed_at":"2026-08-04T19:27:38.464766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.467562Z","title":"Adversarial Sample Detection for Speaker Verification By Neural V ocoders,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.467562Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:ff9801d35355078cb42ff2a049d3f3358840fc30b1ad9d0cb8320dfd0fedeee6","observation_id":"6d1337de-3f43-4ec4-baaa-a83f822a0cd8","resolution":{"observed_at":"2026-08-04T19:27:38.467562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.470581Z","title":"Improving the Adversarial Robustness for Speaker Verification by Self-supervised Learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.470581Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:adb5334bff472d254848c60507c4e0236ef06ec740d0a82ea24805e88fff48ab","observation_id":"a330ab30-da93-4db3-a34e-4ae3025bd56f","resolution":{"observed_at":"2026-08-04T19:27:38.470581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.473589Z","title":"LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.473589Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:6e4ae1bf9d374940d73667c9c7b356414ada1976e5bd332a76b81771882e53ea","observation_id":"95dbda95-5d8f-43cb-b082-b71aceb8e94a","resolution":{"observed_at":"2026-08-04T19:27:38.473589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.476364Z","title":"Defending against Adver- sarial Audio via Diffusion Model,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.476364Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:aab0c5c84090060a15c1b546f60d389b9041c67972b731130dbcae247a1f7660","observation_id":"83e5ea49-e252-4400-ac6d-38f79b4ae678","resolution":{"observed_at":"2026-08-04T19:27:38.476364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.479091Z","title":"FoolHD: Fooling Speaker Identification By Highly Imperceptible Adversarial Disturbances,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.479091Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:0b361305685fc5f989843d47a5ed75aff1bbda12b189b294a2e20423b26b19f3","observation_id":"70e783ef-bdcc-4bb2-bfe1-f2541f3eba65","resolution":{"observed_at":"2026-08-04T19:27:38.479091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.481927Z","title":"Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.481927Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:a458ab87ce630adafa53457c3003484ad63c715f48f8aef3356989d4f14892dd","observation_id":"21cd331b-c59d-4f8c-b47d-6ca28a0f8dee","resolution":{"observed_at":"2026-08-04T19:27:38.481927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.485199Z","title":"Speaker-specific Utterance En- semble Based Transfer Attack on Speaker Identification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.485199Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:bc0debfb45b69b90ca29ef583a338a40d1c78df075528f6cdb86a83a65a3aab6","observation_id":"e8959a6b-1665-4098-bd2d-7b17c5ec1ad0","resolution":{"observed_at":"2026-08-04T19:27:38.485199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.488098Z","title":"Interpretable Spectrum Transformation Attacks to Speaker Recognition Systems,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.488098Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:ba288a81f495d36032bcb5927eedbb5f502a28567fb93c24899677a17128bdb3","observation_id":"9be715c9-640d-4e6a-9d8d-ff7f309625cc","resolution":{"observed_at":"2026-08-04T19:27:38.488098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.490910Z","title":"Real-time, Universal, and Robust Adversarial Attacks against Speaker Recognition Systems,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.490910Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:e37661c37e7ce5becd44a23260e2f7cbd269f4bd08f17af4118626434d56b80f","observation_id":"16fdd9bc-b113-4e11-a670-fac97455173c","resolution":{"observed_at":"2026-08-04T19:27:38.490910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.493613Z","title":"CommanderSong: A Systematic Approach for Practical Adversarial V oice Recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.493613Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:6cfc3775731bb16d79682c4ccb5dcdf82ff21c6cfb53d468cd23cb9aea2bf728","observation_id":"4deeefa8-7a6f-4577-8766-a885277da6bb","resolution":{"observed_at":"2026-08-04T19:27:38.493613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.496748Z","title":"Black-Box Adversarial Attacks on Commercial Speech Platforms with Minimal Information,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.496748Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:351629812dafb7a4ab4d833d8884b7998d7c07408c9c766579975b430c1d732f","observation_id":"0011003a-c5d5-4913-a243-990fc8b39649","resolution":{"observed_at":"2026-08-04T19:27:38.496748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.499733Z","title":"QFA2SR: Query-Free Ad- versarial Transfer Attacks to Speaker Recognition Systems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.499733Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:9cdc690d4201719c49f0374bdf7a3fcc2ac4bc6b157467c68d939b476921a353","observation_id":"133428ce-8164-4643-8b50-922b1e510ac7","resolution":{"observed_at":"2026-08-04T19:27:38.499733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.502583Z","title":"Effective and Inconspicuous Over-the-air Adversarial Examples with Adaptive Filtering,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.502583Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:8f334b1e888a0a638ce736dc4992aef3a0a1417e6cef52a74b9a1a4d665d6d44","observation_id":"1e3966f3-53bc-4f64-8511-38e94ba2eca5","resolution":{"observed_at":"2026-08-04T19:27:38.502583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.505355Z","title":"UTIO: Universal, Targeted, Im- perceptible and Over-the-air Audio Adversarial Example,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.505355Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:a1e14a9467efe7679c7735fce7bd3ea48603ef3093df6995d39165967a04e19b","observation_id":"abbaffdd-d7bc-4984-997d-6fd13308bd13","resolution":{"observed_at":"2026-08-04T19:27:38.505355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04582","last_updated":"2024-06-07T02:03:27Z","snapshot_observed_at":"2026-07-06T18:26:54.963211Z","submitted_at":"2024-06-07T02:03:27Z","title":"Neural Codec-based Adversarial Sample Detection for Speaker Verification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04582","snapshot_observed_at":"2026-08-04T19:27:38.508044Z","title":"Neural Codec- based Adversarial Sample Detection for Speaker Verification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.508044Z"},"links":{"cited_paper":"/paper/2406.04582","citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:10dc1549dcbc33ad45148d5c623ec0289ab703eaab980a7b303a9d1cebc5b648","observation_id":"5ac9661d-5a89-47a8-a473-6676d7ff6602","resolution":{"observed_at":"2026-08-04T19:27:38.508044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.511179Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.511179Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:dddc251ffb917387b3396061a9618c9c288c82fcb68f93afe75013cdc263e487","observation_id":"88ebf3e8-b178-4684-b17b-e03373ef44de","resolution":{"observed_at":"2026-08-04T19:27:38.511179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09911","last_updated":"2024-09-16T11:35:38Z","snapshot_observed_at":"2026-08-02T06:29:19.825166Z","submitted_at":"2023-12-15T16:23:21Z","title":"Amphion: An Open-Source Audio, Music and Speech Generation Toolkit","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09911","snapshot_observed_at":"2026-08-04T19:27:38.513900Z","title":"Amphion: An Open-Source Audio, Music and Speech Generation Toolkit,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.513900Z"},"links":{"cited_paper":"/paper/2312.09911","citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:199dfd87e7023b1f1b6f2abb9c86fae81cac76dc8b0a431bca9b84e5a3240ec2","observation_id":"4e784a7e-a083-4458-9281-3654b84f2074","resolution":{"observed_at":"2026-08-04T19:27:38.513900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05361","last_updated":"2024-09-07T15:08:24Z","snapshot_observed_at":"2026-08-07T13:19:22.496186Z","submitted_at":"2024-07-07T13:24:54Z","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05361","snapshot_observed_at":"2026-08-04T19:27:38.516808Z","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.516808Z"},"links":{"cited_paper":"/paper/2407.05361","citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:a97043ed2da717a14eefc4a9c20503f1189798bb87616b55302e2ca040c67b2b","observation_id":"8623222a-d6e0-4eec-9ba4-f132b042c462","resolution":{"observed_at":"2026-08-04T19:27:38.516808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.519758Z","title":"Wave-U-Net: A Multi-scale Neural Network for End-to-end Audio Source Separation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.519758Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:5dcc68902dc25538991338bd59a1dd1187dc8d99c139dd226b8a65d8302aa60f","observation_id":"62a1e95b-9856-4c1d-859f-0680d0652ae3","resolution":{"observed_at":"2026-08-04T19:27:38.519758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.522275Z","title":"Deep One-class Classification,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.522275Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:f8ed1ef23418fab7da9f416fbc8833122dc3fd7e5c54e384a18f85ffbdcd6fcc","observation_id":"b91816a4-e03c-4163-b4da-44ab02388d55","resolution":{"observed_at":"2026-08-04T19:27:38.522275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.524848Z","title":"Wav2vec 2.0: A Framework for Self-supervised Learning of Speech Representations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.524848Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:25fcd1da4c3092a7a79412a5e481aceb4ef4a7ca15e19177f72bc33e3f99ccd9","observation_id":"55342029-c786-4b4c-b6b0-1f448dd92ae4","resolution":{"observed_at":"2026-08-04T19:27:38.524848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.527237Z","title":"Self-supervised Speech Representation Learning: A Review,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.527237Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:0a1301743d03cb8e970248a6b3d6e5250323f6cf2d4063ca8c6d2f3d8b63a72d","observation_id":"ad1cfe73-187e-42fc-afa4-635470ff9eb0","resolution":{"observed_at":"2026-08-04T19:27:38.527237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.529728Z","title":"Libri-Light: A Benchmark for Asr with Limited Or No Supervision,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.529728Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:56758839977360392901a58445fe826a153eeea3af96bb948628567a5e74e493","observation_id":"39faff29-e06d-48b7-982f-5539422ffe57","resolution":{"observed_at":"2026-08-04T19:27:38.529728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.532111Z","title":"V oxCeleb2: Deep Speaker Recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.532111Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:94ad9acec78965d572b4841c8f16c420de054be819fe839d4816807364f58007","observation_id":"c9d58d29-73fe-4c9f-ab94-d69d6a9dd008","resolution":{"observed_at":"2026-08-04T19:27:38.532111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.534607Z","title":"A Kernel Method for the Two-sample-problem,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.534607Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:f53938baaacef2371076cf33c127b8dc3daee11d44dc06a73822415a0ae93942","observation_id":"afc1c048-52e8-4e50-8da6-7d91fd894a13","resolution":{"observed_at":"2026-08-04T19:27:38.534607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.537132Z","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in Tdnn Based Speaker Verification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.537132Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:375ca7a5af8a692436abfb6d02942c55868bf491ee46c3aec0f70ccb8eecbc70","observation_id":"26fdd8f8-da11-4814-9cb4-4ac9e148cd74","resolution":{"observed_at":"2026-08-04T19:27:38.537132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.539587Z","title":"X- Vectors: Robust Dnn Embeddings for Speaker Recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.539587Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:8cbc0410fd24c4a36631c3c1d044bc21659ec05f66b3b5b62a44c18b4f95ab72","observation_id":"4a26c303-dd65-4d05-b2ee-1c592f2b2940","resolution":{"observed_at":"2026-08-04T19:27:38.539587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.542159Z","title":"The Ins and Outs of Speaker Recognition: Lessons From V oxsrc 2020,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.542159Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:36de2dc7dde48eaa6cdec802d8642271febdd66e3084c9690ed536dd5f053961","observation_id":"fb51a6ca-a3ce-4df0-b8ea-1ee6bf370248","resolution":{"observed_at":"2026-08-04T19:27:38.542159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.544463Z","title":"Pushing the Limits of Raw Waveform Speaker Recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.544463Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:57ac943eee141810a63940cfaa6e1d9867035287d7c69f60fa8a4cd86f95f29e","observation_id":"46faf9b5-f2dc-412e-98a1-a1105033070d","resolution":{"observed_at":"2026-08-04T19:27:38.544463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.546896Z","title":"V oxCeleb: A Large-scale Speaker Identification Dataset,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.546896Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:9792ab0730bba1e0dcd96a4dc9cc1e2581f517cc4a4c543ca10e77b9f0bf6977","observation_id":"64dafd7f-c3b2-49ee-a85d-3045947d8d7b","resolution":{"observed_at":"2026-08-04T19:27:38.546896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.549422Z","title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR V oice Cloning Toolkit,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.549422Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:df80eaa48f7e2926784c23c03dbc606d3bcbc2c498368dc68741f23c71202b70","observation_id":"556a9932-7ba2-435c-9666-4109c68c4258","resolution":{"observed_at":"2026-08-04T19:27:38.549422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.551953Z","title":"Parallel Wavegan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-resolution Spectrogram,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.551953Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:c29de3c1df87e97aa549ce8713f6c3d381c85cb8b5b2350fc54e1cab98d8be46","observation_id":"15e9fc80-7cbc-440d-be9b-ca88224da344","resolution":{"observed_at":"2026-08-04T19:27:38.551953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:27:38.554271Z","title":"Visualizing Data Using T-SNE","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T19:27:38.554271Z"},"links":{"citing_paper":"/paper/2509.09296"},"observation_digest":"sha256:2c2cdf373903a0ce568921ef9ba87bbb81f6b22a7d414f0215892f44164e612b","observation_id":"7ef4410e-c3f4-4567-94cb-570e9caae000","resolution":{"observed_at":"2026-08-04T19:27:38.554271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09296","last_updated":"2025-09-11T09:36:31Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-04T19:27:37.669061Z","submitted_at":"2025-09-11T09:36:31Z","title":"Over-the-Air Adversarial Attack Detection: from Datasets to Defenses"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2509.09296."}