{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4OXATR6WVOILEKDDLH4E7K6J2T","short_pith_number":"pith:4OXATR6W","schema_version":"1.0","canonical_sha256":"e3ae09c7d6ab90b2286359f84fabc9d4ddf9902ba773c769146d4955a5466246","source":{"kind":"arxiv","id":"2005.14611","version":2},"attestation_state":"computed","paper":{"title":"Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Asja Fischer, Dorothea Kolossa, Lea Sch\\\"onherr, Sina D\\\"aubener","submitted_at":"2020-05-24T19:31:02Z","abstract_excerpt":"Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases are targeted attacks, in which an attacker aims to force the system into recognizing given target transcriptions in an arbitrary audio sample. The increasing number of sophisticated, quasi imperceptible attacks raises the question of countermeasures. In this paper, we focus on hybrid ASR systems and compare four acoustic models regarding their ability to ind"},"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":"2005.14611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-24T19:31:02Z","cross_cats_sorted":["cs.CR","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"b381c2f5f350af4fbaff272e0d316fef9c3f6e629aac13f0c3167410aebfcd47","abstract_canon_sha256":"2b4cf9995239225de03f37ffb37b22d0bdc0fde4621c93049a466a92fd676b92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:00.493061Z","signature_b64":"sJfZPTwL+EC2asUpgTKbo5XngJSoFLtgOLxqFzJzLf8OlvwP5+rqUAHJQVOQYj5EMeFI81PwW8u0gOGNzui/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ae09c7d6ab90b2286359f84fabc9d4ddf9902ba773c769146d4955a5466246","last_reissued_at":"2026-07-05T01:24:00.492644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:00.492644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Asja Fischer, Dorothea Kolossa, Lea Sch\\\"onherr, Sina D\\\"aubener","submitted_at":"2020-05-24T19:31:02Z","abstract_excerpt":"Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases are targeted attacks, in which an attacker aims to force the system into recognizing given target transcriptions in an arbitrary audio sample. The increasing number of sophisticated, quasi imperceptible attacks raises the question of countermeasures. In this paper, we focus on hybrid ASR systems and compare four acoustic models regarding their ability to ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14611","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.14611/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":"2005.14611","created_at":"2026-07-05T01:24:00.492693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.14611v2","created_at":"2026-07-05T01:24:00.492693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14611","created_at":"2026-07-05T01:24:00.492693+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OXATR6WVOIL","created_at":"2026-07-05T01:24:00.492693+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OXATR6WVOILEKDD","created_at":"2026-07-05T01:24:00.492693+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OXATR6W","created_at":"2026-07-05T01:24:00.492693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.01551","citing_title":"Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T","json":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T.json","graph_json":"https://pith.science/api/pith-number/4OXATR6WVOILEKDDLH4E7K6J2T/graph.json","events_json":"https://pith.science/api/pith-number/4OXATR6WVOILEKDDLH4E7K6J2T/events.json","paper":"https://pith.science/paper/4OXATR6W"},"agent_actions":{"view_html":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T","download_json":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T.json","view_paper":"https://pith.science/paper/4OXATR6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.14611&json=true","fetch_graph":"https://pith.science/api/pith-number/4OXATR6WVOILEKDDLH4E7K6J2T/graph.json","fetch_events":"https://pith.science/api/pith-number/4OXATR6WVOILEKDDLH4E7K6J2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T/action/storage_attestation","attest_author":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T/action/author_attestation","sign_citation":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T/action/citation_signature","submit_replication":"https://pith.science/pith/4OXATR6WVOILEKDDLH4E7K6J2T/action/replication_record"}},"created_at":"2026-07-05T01:24:00.492693+00:00","updated_at":"2026-07-05T01:24:00.492693+00:00"}