{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JDSA5GOSA7YKQ7MTDNYGSRNV7F","short_pith_number":"pith:JDSA5GOS","schema_version":"1.0","canonical_sha256":"48e40e99d207f0a87d931b706945b5f976e6b6908d8a9e69f966e1b7e5608b86","source":{"kind":"arxiv","id":"2006.06356","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.CR","authors_text":"Bart Liefers, Bram van Ginneken, Clara I. S\\'anchez, Cristina Gonz\\'alez-Gonzalo, Florian Dubost, Gerda Bortsova, Ioannis Katramados, Josien P.W. Pluim, Laurens Hogeweg, Marleen de Bruijne, Mitko Veta, Suzanne C. Wetstein","submitted_at":"2020-06-11T12:19:39Z","abstract_excerpt":"Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure.\n  In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model"},"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":"2006.06356","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-06-11T12:19:39Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"d934dc488fbd29b3b574c730fbedb86c150e2e51e2f807e0c41187d7361a3bc5","abstract_canon_sha256":"1962e05ec4478ccfbf5d42a50b4e275083b73fa3fe380ba6e96ec7f73ece7650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:07.543427Z","signature_b64":"Lvb52cnAzQK1SoSnzeFSLXWH3ICQVOLzYd9MebILSH0V9TbEVRmoKPRFh8buCEngwjjTKdcPcFU+RZcBZRf0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48e40e99d207f0a87d931b706945b5f976e6b6908d8a9e69f966e1b7e5608b86","last_reissued_at":"2026-07-05T02:51:07.542967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:07.542967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.CR","authors_text":"Bart Liefers, Bram van Ginneken, Clara I. S\\'anchez, Cristina Gonz\\'alez-Gonzalo, Florian Dubost, Gerda Bortsova, Ioannis Katramados, Josien P.W. Pluim, Laurens Hogeweg, Marleen de Bruijne, Mitko Veta, Suzanne C. Wetstein","submitted_at":"2020-06-11T12:19:39Z","abstract_excerpt":"Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure.\n  In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06356","kind":"arxiv","version":3},"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/2006.06356/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":"2006.06356","created_at":"2026-07-05T02:51:07.543025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06356v3","created_at":"2026-07-05T02:51:07.543025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06356","created_at":"2026-07-05T02:51:07.543025+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDSA5GOSA7YK","created_at":"2026-07-05T02:51:07.543025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDSA5GOSA7YKQ7MT","created_at":"2026-07-05T02:51:07.543025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDSA5GOS","created_at":"2026-07-05T02:51:07.543025+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/JDSA5GOSA7YKQ7MTDNYGSRNV7F","json":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F.json","graph_json":"https://pith.science/api/pith-number/JDSA5GOSA7YKQ7MTDNYGSRNV7F/graph.json","events_json":"https://pith.science/api/pith-number/JDSA5GOSA7YKQ7MTDNYGSRNV7F/events.json","paper":"https://pith.science/paper/JDSA5GOS"},"agent_actions":{"view_html":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F","download_json":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F.json","view_paper":"https://pith.science/paper/JDSA5GOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06356&json=true","fetch_graph":"https://pith.science/api/pith-number/JDSA5GOSA7YKQ7MTDNYGSRNV7F/graph.json","fetch_events":"https://pith.science/api/pith-number/JDSA5GOSA7YKQ7MTDNYGSRNV7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F/action/storage_attestation","attest_author":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F/action/author_attestation","sign_citation":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F/action/citation_signature","submit_replication":"https://pith.science/pith/JDSA5GOSA7YKQ7MTDNYGSRNV7F/action/replication_record"}},"created_at":"2026-07-05T02:51:07.543025+00:00","updated_at":"2026-07-05T02:51:07.543025+00:00"}