{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3YE3LZUU3TJPF2K7LP7G6FVHXQ","short_pith_number":"pith:3YE3LZUU","schema_version":"1.0","canonical_sha256":"de09b5e694dcd2f2e95f5bfe6f16a7bc2cd51e032749beaf8ce8c9bfd0959e80","source":{"kind":"arxiv","id":"2109.09598","version":1},"attestation_state":"computed","paper":{"title":"\"Hello, It's Me\": Deep Learning-based Speech Synthesis Attacks in the Real World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Angela Sha, Ben Y. Zhao, Christian Cianfarani, Emily Wenger, Haitao Zheng, Jenna Cryan, Max Bronckers","submitted_at":"2021-09-20T14:53:22Z","abstract_excerpt":"Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both humans and software systems (aka machines). This paper documents efforts and findings from a comprehensive experimental study on the impact of deep-learning based speech synthesis attacks on both human listeners and machines such as speaker recognition and voice-signin systems. We find that both humans and machines can be reliably fooled by synthet"},"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":"2109.09598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-09-20T14:53:22Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e12d31e5fdbd6574cd934d12f0abd15427359f895d02de29dddbe7fad189b493","abstract_canon_sha256":"60dce3b162c183f57f1fc3471ab6a855bf81eea0f6f454736ca74faf73712c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:47.775808Z","signature_b64":"KZT6ObDAR0cNN1FKZGPSfpxgVd9jnwnu+yXAe8BS4D8fkKUc7i67oZ/4tmGGjHoOr61C17GIYQHr5Yrfk12hBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de09b5e694dcd2f2e95f5bfe6f16a7bc2cd51e032749beaf8ce8c9bfd0959e80","last_reissued_at":"2026-07-05T03:15:47.775168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:47.775168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Hello, It's Me\": Deep Learning-based Speech Synthesis Attacks in the Real World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Angela Sha, Ben Y. Zhao, Christian Cianfarani, Emily Wenger, Haitao Zheng, Jenna Cryan, Max Bronckers","submitted_at":"2021-09-20T14:53:22Z","abstract_excerpt":"Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both humans and software systems (aka machines). This paper documents efforts and findings from a comprehensive experimental study on the impact of deep-learning based speech synthesis attacks on both human listeners and machines such as speaker recognition and voice-signin systems. We find that both humans and machines can be reliably fooled by synthet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09598","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/2109.09598/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":"2109.09598","created_at":"2026-07-05T03:15:47.775226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09598v1","created_at":"2026-07-05T03:15:47.775226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09598","created_at":"2026-07-05T03:15:47.775226+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YE3LZUU3TJP","created_at":"2026-07-05T03:15:47.775226+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YE3LZUU3TJPF2K7","created_at":"2026-07-05T03:15:47.775226+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YE3LZUU","created_at":"2026-07-05T03:15:47.775226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.04230","citing_title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ","json":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ.json","graph_json":"https://pith.science/api/pith-number/3YE3LZUU3TJPF2K7LP7G6FVHXQ/graph.json","events_json":"https://pith.science/api/pith-number/3YE3LZUU3TJPF2K7LP7G6FVHXQ/events.json","paper":"https://pith.science/paper/3YE3LZUU"},"agent_actions":{"view_html":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ","download_json":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ.json","view_paper":"https://pith.science/paper/3YE3LZUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09598&json=true","fetch_graph":"https://pith.science/api/pith-number/3YE3LZUU3TJPF2K7LP7G6FVHXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3YE3LZUU3TJPF2K7LP7G6FVHXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ/action/storage_attestation","attest_author":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ/action/author_attestation","sign_citation":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ/action/citation_signature","submit_replication":"https://pith.science/pith/3YE3LZUU3TJPF2K7LP7G6FVHXQ/action/replication_record"}},"created_at":"2026-07-05T03:15:47.775226+00:00","updated_at":"2026-07-05T03:15:47.775226+00:00"}