{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WI2TFCICIXCSHDQ5H3H7EZS2BK","short_pith_number":"pith:WI2TFCIC","schema_version":"1.0","canonical_sha256":"b23532890245c5238e1d3ecff2665a0a8e1600b5257553a9fb111e4dc2cba92c","source":{"kind":"arxiv","id":"2010.10682","version":3},"attestation_state":"computed","paper":{"title":"VenoMave: Targeted Poisoning Against Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Christopher Kruegel, Dorothea Kolossa, Giovanni Vigna, Hojjat Aghakhani, Lea Sch\\\"onherr, Thorsten Eisenhofer, Thorsten Holz","submitted_at":"2020-10-21T00:30:08Z","abstract_excerpt":"Despite remarkable improvements, automatic speech recognition is susceptible to adversarial perturbations. Compared to standard machine learning architectures, these attacks are significantly more challenging, especially since the inputs to a speech recognition system are time series that contain both acoustic and linguistic properties of speech. Extracting all recognition-relevant information requires more complex pipelines and an ensemble of specialized components. Consequently, an attacker needs to consider the entire pipeline. In this paper, we present VENOMAVE, the first training-time poi"},"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":"2010.10682","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-21T00:30:08Z","cross_cats_sorted":["cs.CR","cs.LG","eess.AS"],"title_canon_sha256":"fd864d050e115a9b15cae86d407cfd8d9a10e38be1baacdcca7496d293a299e9","abstract_canon_sha256":"1266943182b92423aba4f1c3d41fa295420e7cbcfe7a59a08896daa161a0e2a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:05.620324Z","signature_b64":"hqW1Fjd6z2B2rlvYGPoN97AjPmD8xtxHqXuHE8Ma7lHTAMj/5zUWbeo+UcEZJCpr1sLlC12UqQxyLtVQ+U+8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b23532890245c5238e1d3ecff2665a0a8e1600b5257553a9fb111e4dc2cba92c","last_reissued_at":"2026-07-05T06:03:05.619890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:05.619890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VenoMave: Targeted Poisoning Against Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Christopher Kruegel, Dorothea Kolossa, Giovanni Vigna, Hojjat Aghakhani, Lea Sch\\\"onherr, Thorsten Eisenhofer, Thorsten Holz","submitted_at":"2020-10-21T00:30:08Z","abstract_excerpt":"Despite remarkable improvements, automatic speech recognition is susceptible to adversarial perturbations. Compared to standard machine learning architectures, these attacks are significantly more challenging, especially since the inputs to a speech recognition system are time series that contain both acoustic and linguistic properties of speech. Extracting all recognition-relevant information requires more complex pipelines and an ensemble of specialized components. Consequently, an attacker needs to consider the entire pipeline. In this paper, we present VENOMAVE, the first training-time poi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10682","kind":"arxiv","version":3},"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/2010.10682/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":"2010.10682","created_at":"2026-07-05T06:03:05.619950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.10682v3","created_at":"2026-07-05T06:03:05.619950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10682","created_at":"2026-07-05T06:03:05.619950+00:00"},{"alias_kind":"pith_short_12","alias_value":"WI2TFCICIXCS","created_at":"2026-07-05T06:03:05.619950+00:00"},{"alias_kind":"pith_short_16","alias_value":"WI2TFCICIXCSHDQ5","created_at":"2026-07-05T06:03:05.619950+00:00"},{"alias_kind":"pith_short_8","alias_value":"WI2TFCIC","created_at":"2026-07-05T06:03:05.619950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28953","citing_title":"Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK","json":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK.json","graph_json":"https://pith.science/api/pith-number/WI2TFCICIXCSHDQ5H3H7EZS2BK/graph.json","events_json":"https://pith.science/api/pith-number/WI2TFCICIXCSHDQ5H3H7EZS2BK/events.json","paper":"https://pith.science/paper/WI2TFCIC"},"agent_actions":{"view_html":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK","download_json":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK.json","view_paper":"https://pith.science/paper/WI2TFCIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.10682&json=true","fetch_graph":"https://pith.science/api/pith-number/WI2TFCICIXCSHDQ5H3H7EZS2BK/graph.json","fetch_events":"https://pith.science/api/pith-number/WI2TFCICIXCSHDQ5H3H7EZS2BK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK/action/storage_attestation","attest_author":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK/action/author_attestation","sign_citation":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK/action/citation_signature","submit_replication":"https://pith.science/pith/WI2TFCICIXCSHDQ5H3H7EZS2BK/action/replication_record"}},"created_at":"2026-07-05T06:03:05.619950+00:00","updated_at":"2026-07-05T06:03:05.619950+00:00"}