{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N3ZB67TO3GE4QPVVL2NK7OE2PD","short_pith_number":"pith:N3ZB67TO","schema_version":"1.0","canonical_sha256":"6ef21f7e6ed989c83eb55e9aafb89a78fea8533dc35bb55f4fea237f2073a83f","source":{"kind":"arxiv","id":"2106.09223","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jueming Hu, Sheng Cheng, Yongming Liu, Yutian Pang","submitted_at":"2021-06-17T03:18:59Z","abstract_excerpt":"To evaluate the robustness gain of Bayesian neural networks on image classification tasks, we perform input perturbations, and adversarial attacks to the state-of-the-art Bayesian neural networks, with a benchmark CNN model as reference. The attacks are selected to simulate signal interference and cyberattacks towards CNN-based machine learning systems. The result shows that a Bayesian neural network achieves significantly higher robustness against adversarial attacks generated against a deterministic neural network model, without adversarial training. The Bayesian posterior can act as the saf"},"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":"2106.09223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T03:18:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c0154120658f50949a89bffc41cd7465cc75fbe5b9a14de97ff4e10ea4d4a67","abstract_canon_sha256":"d1b4edbbdaee82c946674eb4515707889306f23272a3d7473fe81462ede0bf3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:13.696410Z","signature_b64":"mlPlZjVHNy5J4hR/uJt1B/5jo95ETTCLYWn7Dn5DQ3dK0NQtw/BKcyj0kdPd+YLXK+kESrn9mw0HyBqWBH4vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef21f7e6ed989c83eb55e9aafb89a78fea8533dc35bb55f4fea237f2073a83f","last_reissued_at":"2026-07-05T02:50:13.696054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:13.696054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jueming Hu, Sheng Cheng, Yongming Liu, Yutian Pang","submitted_at":"2021-06-17T03:18:59Z","abstract_excerpt":"To evaluate the robustness gain of Bayesian neural networks on image classification tasks, we perform input perturbations, and adversarial attacks to the state-of-the-art Bayesian neural networks, with a benchmark CNN model as reference. The attacks are selected to simulate signal interference and cyberattacks towards CNN-based machine learning systems. The result shows that a Bayesian neural network achieves significantly higher robustness against adversarial attacks generated against a deterministic neural network model, without adversarial training. The Bayesian posterior can act as the saf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09223","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/2106.09223/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":"2106.09223","created_at":"2026-07-05T02:50:13.696114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09223v1","created_at":"2026-07-05T02:50:13.696114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09223","created_at":"2026-07-05T02:50:13.696114+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3ZB67TO3GE4","created_at":"2026-07-05T02:50:13.696114+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3ZB67TO3GE4QPVV","created_at":"2026-07-05T02:50:13.696114+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3ZB67TO","created_at":"2026-07-05T02:50:13.696114+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/N3ZB67TO3GE4QPVVL2NK7OE2PD","json":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD.json","graph_json":"https://pith.science/api/pith-number/N3ZB67TO3GE4QPVVL2NK7OE2PD/graph.json","events_json":"https://pith.science/api/pith-number/N3ZB67TO3GE4QPVVL2NK7OE2PD/events.json","paper":"https://pith.science/paper/N3ZB67TO"},"agent_actions":{"view_html":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD","download_json":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD.json","view_paper":"https://pith.science/paper/N3ZB67TO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09223&json=true","fetch_graph":"https://pith.science/api/pith-number/N3ZB67TO3GE4QPVVL2NK7OE2PD/graph.json","fetch_events":"https://pith.science/api/pith-number/N3ZB67TO3GE4QPVVL2NK7OE2PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD/action/storage_attestation","attest_author":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD/action/author_attestation","sign_citation":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD/action/citation_signature","submit_replication":"https://pith.science/pith/N3ZB67TO3GE4QPVVL2NK7OE2PD/action/replication_record"}},"created_at":"2026-07-05T02:50:13.696114+00:00","updated_at":"2026-07-05T02:50:13.696114+00:00"}