{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5EKYXYMVWX5ZSFLCMT52KNI5P3","short_pith_number":"pith:5EKYXYMV","schema_version":"1.0","canonical_sha256":"e9158be195b5fb99156264fba5351d7ec2a9615979175b0060c17ff72a9cc3f5","source":{"kind":"arxiv","id":"2404.15854","version":1},"attestation_state":"computed","paper":{"title":"CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Cong Wu, Guowen Xu, Haolin Wu, Hao Ren, Jing Chen, Kun He, Ruiying Du, Xingcan Shang","submitted_at":"2024-04-24T13:10:35Z","abstract_excerpt":"The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains underexplored. To bridge the gap, we undertake the first comprehensive study of the susceptibility of the most widely adopted audio deepfake detectors to manipulation attacks. Surprisingly, even manipulations like volume control can significantly bypass detection without affecting human perception. To address this, we propose CLAD (Contrastive Learning-based Audio"},"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":"2404.15854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-04-24T13:10:35Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"500ecccbb52ba30c28377fdb84b18650716756bfb94113d269264e30886a276a","abstract_canon_sha256":"8b369184463792d4ad5c09ec13a2bde14b59c010e429f689ec84e77c867ccf2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:46.538282Z","signature_b64":"eEWnk5ujF7yVu/rdqQUNS+tKWGk3PBkhWhFc5/iKtLKUN42c1jwU2lMqk3YCPZoC/lIFj+av2Yib6hjWThlTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9158be195b5fb99156264fba5351d7ec2a9615979175b0060c17ff72a9cc3f5","last_reissued_at":"2026-07-05T08:11:46.537813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:46.537813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CR","authors_text":"Cong Wu, Guowen Xu, Haolin Wu, Hao Ren, Jing Chen, Kun He, Ruiying Du, Xingcan Shang","submitted_at":"2024-04-24T13:10:35Z","abstract_excerpt":"The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains underexplored. To bridge the gap, we undertake the first comprehensive study of the susceptibility of the most widely adopted audio deepfake detectors to manipulation attacks. Surprisingly, even manipulations like volume control can significantly bypass detection without affecting human perception. To address this, we propose CLAD (Contrastive Learning-based Audio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15854","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/2404.15854/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":"2404.15854","created_at":"2026-07-05T08:11:46.537867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15854v1","created_at":"2026-07-05T08:11:46.537867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15854","created_at":"2026-07-05T08:11:46.537867+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EKYXYMVWX5Z","created_at":"2026-07-05T08:11:46.537867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EKYXYMVWX5ZSFLC","created_at":"2026-07-05T08:11:46.537867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EKYXYMV","created_at":"2026-07-05T08:11:46.537867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29544","citing_title":"Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23201","citing_title":"MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26057","citing_title":"Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3","json":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3.json","graph_json":"https://pith.science/api/pith-number/5EKYXYMVWX5ZSFLCMT52KNI5P3/graph.json","events_json":"https://pith.science/api/pith-number/5EKYXYMVWX5ZSFLCMT52KNI5P3/events.json","paper":"https://pith.science/paper/5EKYXYMV"},"agent_actions":{"view_html":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3","download_json":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3.json","view_paper":"https://pith.science/paper/5EKYXYMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15854&json=true","fetch_graph":"https://pith.science/api/pith-number/5EKYXYMVWX5ZSFLCMT52KNI5P3/graph.json","fetch_events":"https://pith.science/api/pith-number/5EKYXYMVWX5ZSFLCMT52KNI5P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3/action/storage_attestation","attest_author":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3/action/author_attestation","sign_citation":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3/action/citation_signature","submit_replication":"https://pith.science/pith/5EKYXYMVWX5ZSFLCMT52KNI5P3/action/replication_record"}},"created_at":"2026-07-05T08:11:46.537867+00:00","updated_at":"2026-07-05T08:11:46.537867+00:00"}