{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KAPA67HN7YECU4RYX66I4GGEOQ","short_pith_number":"pith:KAPA67HN","schema_version":"1.0","canonical_sha256":"501e0f7cedfe082a7238bfbc8e18c4742600057ddd93602f0be2c064f8917244","source":{"kind":"arxiv","id":"2103.03344","version":1},"attestation_state":"computed","paper":{"title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Farinaz Koushanfar, Julian McAuley, Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov","submitted_at":"2021-03-04T21:44:37Z","abstract_excerpt":"There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR systems in safety-critical applications. In this work, we introduce WaveGuard: a framework for detecting adversarial inputs that are crafted to attack ASR systems. Our framework incorporates audio transformation functions and analyses the ASR transcriptions of the original and transformed audio to detect adversarial inputs. We demonstrate that our defense framewor"},"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":"2103.03344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-03-04T21:44:37Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"72d4258236460b8d94048b40e9ada31911063f00886cd89f952c1ce6205181d9","abstract_canon_sha256":"7648fecbeb1baff3781f25c829b0577822f508a8da8d2f01bf3997fa53aff3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:34.034775Z","signature_b64":"TpuScV6r6pn0KfnjErmG4Ud4vYDMrgj2PQ0jevgPK2i6Judhk5ZTc154w3TjtcV88m2uSz+m85za6GTtSGPYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"501e0f7cedfe082a7238bfbc8e18c4742600057ddd93602f0be2c064f8917244","last_reissued_at":"2026-07-05T02:20:34.034153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:34.034153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Farinaz Koushanfar, Julian McAuley, Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov","submitted_at":"2021-03-04T21:44:37Z","abstract_excerpt":"There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR systems in safety-critical applications. In this work, we introduce WaveGuard: a framework for detecting adversarial inputs that are crafted to attack ASR systems. Our framework incorporates audio transformation functions and analyses the ASR transcriptions of the original and transformed audio to detect adversarial inputs. We demonstrate that our defense framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03344","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/2103.03344/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":"2103.03344","created_at":"2026-07-05T02:20:34.034216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03344v1","created_at":"2026-07-05T02:20:34.034216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03344","created_at":"2026-07-05T02:20:34.034216+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAPA67HN7YEC","created_at":"2026-07-05T02:20:34.034216+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAPA67HN7YECU4RY","created_at":"2026-07-05T02:20:34.034216+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAPA67HN","created_at":"2026-07-05T02:20:34.034216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ","json":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ.json","graph_json":"https://pith.science/api/pith-number/KAPA67HN7YECU4RYX66I4GGEOQ/graph.json","events_json":"https://pith.science/api/pith-number/KAPA67HN7YECU4RYX66I4GGEOQ/events.json","paper":"https://pith.science/paper/KAPA67HN"},"agent_actions":{"view_html":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ","download_json":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ.json","view_paper":"https://pith.science/paper/KAPA67HN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03344&json=true","fetch_graph":"https://pith.science/api/pith-number/KAPA67HN7YECU4RYX66I4GGEOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KAPA67HN7YECU4RYX66I4GGEOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ/action/storage_attestation","attest_author":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ/action/author_attestation","sign_citation":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ/action/citation_signature","submit_replication":"https://pith.science/pith/KAPA67HN7YECU4RYX66I4GGEOQ/action/replication_record"}},"created_at":"2026-07-05T02:20:34.034216+00:00","updated_at":"2026-07-05T02:20:34.034216+00:00"}