{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:43WIE33RQWFFF7C3J6JB55W2DI","short_pith_number":"pith:43WIE33R","schema_version":"1.0","canonical_sha256":"e6ec826f71858a52fc5b4f921ef6da1a0d596d382954047bed32f5cd33f1842b","source":{"kind":"arxiv","id":"2105.00495","version":2},"attestation_state":"computed","paper":{"title":"BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Ambra Demontis, Fabio Roli, Gill Dobbie, J\\\"org Wicker, Kaiqi Zhao, Katharina Dost, Xinglong Chang","submitted_at":"2021-05-02T15:24:33Z","abstract_excerpt":"Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging. Additionally, attackers do not need to follow the rules made by the defender. To address this problem, we take inspiration from the concept of Applicability Domain in cheminformatics. Cheminformatics models struggle to make accurate predictions because only a limited number of compounds are known and available for training. Applicability Domain defines a domain"},"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":"2105.00495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-02T15:24:33Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"4bfd525a05adb8bcd121a47f5ad10af0fb5ab2067cbe55e6325e0f344195d27b","abstract_canon_sha256":"c364bb91582fe0727525075a2a499e556145f8fa4b4646dd4b9fdd94833b76bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:27.017597Z","signature_b64":"8vo+MPL3Srfi/Uz6tdDngkoqYaqZNH6EOxJoJ26s/jw5hmWAEfKD4oFbV+haqXb9+k8+CTta13+DWJbxijdoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6ec826f71858a52fc5b4f921ef6da1a0d596d382954047bed32f5cd33f1842b","last_reissued_at":"2026-07-05T06:50:27.017127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:27.017127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Ambra Demontis, Fabio Roli, Gill Dobbie, J\\\"org Wicker, Kaiqi Zhao, Katharina Dost, Xinglong Chang","submitted_at":"2021-05-02T15:24:33Z","abstract_excerpt":"Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging. Additionally, attackers do not need to follow the rules made by the defender. To address this problem, we take inspiration from the concept of Applicability Domain in cheminformatics. Cheminformatics models struggle to make accurate predictions because only a limited number of compounds are known and available for training. Applicability Domain defines a domain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00495","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/2105.00495/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":"2105.00495","created_at":"2026-07-05T06:50:27.017182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.00495v2","created_at":"2026-07-05T06:50:27.017182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00495","created_at":"2026-07-05T06:50:27.017182+00:00"},{"alias_kind":"pith_short_12","alias_value":"43WIE33RQWFF","created_at":"2026-07-05T06:50:27.017182+00:00"},{"alias_kind":"pith_short_16","alias_value":"43WIE33RQWFFF7C3","created_at":"2026-07-05T06:50:27.017182+00:00"},{"alias_kind":"pith_short_8","alias_value":"43WIE33R","created_at":"2026-07-05T06:50:27.017182+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/43WIE33RQWFFF7C3J6JB55W2DI","json":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI.json","graph_json":"https://pith.science/api/pith-number/43WIE33RQWFFF7C3J6JB55W2DI/graph.json","events_json":"https://pith.science/api/pith-number/43WIE33RQWFFF7C3J6JB55W2DI/events.json","paper":"https://pith.science/paper/43WIE33R"},"agent_actions":{"view_html":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI","download_json":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI.json","view_paper":"https://pith.science/paper/43WIE33R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.00495&json=true","fetch_graph":"https://pith.science/api/pith-number/43WIE33RQWFFF7C3J6JB55W2DI/graph.json","fetch_events":"https://pith.science/api/pith-number/43WIE33RQWFFF7C3J6JB55W2DI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI/action/storage_attestation","attest_author":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI/action/author_attestation","sign_citation":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI/action/citation_signature","submit_replication":"https://pith.science/pith/43WIE33RQWFFF7C3J6JB55W2DI/action/replication_record"}},"created_at":"2026-07-05T06:50:27.017182+00:00","updated_at":"2026-07-05T06:50:27.017182+00:00"}