{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FI3H6NHBNNFD3H3M42ZABZHQG5","short_pith_number":"pith:FI3H6NHB","schema_version":"1.0","canonical_sha256":"2a367f34e16b4a3d9f6ce6b200e4f03756952af248ec64f7e7bd7253bada68e8","source":{"kind":"arxiv","id":"1901.07846","version":2},"attestation_state":"computed","paper":{"title":"SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jinfeng Li, Qinchen Gu, Raheem Beyah, Shouling Ji, Tianyu Du, Ting Wang","submitted_at":"2019-01-23T12:23:07Z","abstract_excerpt":"Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave. In this paper, we present SirenAttack, a new class of attacks to generate adversarial audios. Compared with existing attacks, SirenAttack highlights with a set of significant features: (i) versatile -- it is able to deceive a range of end-to-end acoustic systems under both white-box and black-box settings; (ii) effective -- it is able to generate adversarial audios that can be recognized as specific phra"},"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":"1901.07846","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2019-01-23T12:23:07Z","cross_cats_sorted":[],"title_canon_sha256":"f464bc89ddf6d4fea9aff79e9cc38fa20adc228ebde4a3bc9d94f5a8c76ce53d","abstract_canon_sha256":"460576f2af0b6966a104485d7d35a79f015717502a4b3f09b91482f26f038385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:39.917179Z","signature_b64":"e3SSmZOd4NrW6RqoXIhUxDyGx5B1mbRp9mUbDPCrLLH/ATJINfZDSKmOdkr/rdKzPGi+T134RnSgSmzm4E4GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a367f34e16b4a3d9f6ce6b200e4f03756952af248ec64f7e7bd7253bada68e8","last_reissued_at":"2026-05-17T23:39:39.916452Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:39.916452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jinfeng Li, Qinchen Gu, Raheem Beyah, Shouling Ji, Tianyu Du, Ting Wang","submitted_at":"2019-01-23T12:23:07Z","abstract_excerpt":"Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave. In this paper, we present SirenAttack, a new class of attacks to generate adversarial audios. Compared with existing attacks, SirenAttack highlights with a set of significant features: (i) versatile -- it is able to deceive a range of end-to-end acoustic systems under both white-box and black-box settings; (ii) effective -- it is able to generate adversarial audios that can be recognized as specific phra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07846","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1901.07846","created_at":"2026-05-17T23:39:39.916569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07846v2","created_at":"2026-05-17T23:39:39.916569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07846","created_at":"2026-05-17T23:39:39.916569+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI3H6NHBNNFD","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI3H6NHBNNFD3H3M","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI3H6NHB","created_at":"2026-05-18T12:33:15.570797+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/FI3H6NHBNNFD3H3M42ZABZHQG5","json":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5.json","graph_json":"https://pith.science/api/pith-number/FI3H6NHBNNFD3H3M42ZABZHQG5/graph.json","events_json":"https://pith.science/api/pith-number/FI3H6NHBNNFD3H3M42ZABZHQG5/events.json","paper":"https://pith.science/paper/FI3H6NHB"},"agent_actions":{"view_html":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5","download_json":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5.json","view_paper":"https://pith.science/paper/FI3H6NHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07846&json=true","fetch_graph":"https://pith.science/api/pith-number/FI3H6NHBNNFD3H3M42ZABZHQG5/graph.json","fetch_events":"https://pith.science/api/pith-number/FI3H6NHBNNFD3H3M42ZABZHQG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5/action/storage_attestation","attest_author":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5/action/author_attestation","sign_citation":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5/action/citation_signature","submit_replication":"https://pith.science/pith/FI3H6NHBNNFD3H3M42ZABZHQG5/action/replication_record"}},"created_at":"2026-05-17T23:39:39.916569+00:00","updated_at":"2026-05-17T23:39:39.916569+00:00"}