{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WTVE2UAM6PIR7ALP5NQ6ZSXIZF","short_pith_number":"pith:WTVE2UAM","schema_version":"1.0","canonical_sha256":"b4ea4d500cf3d11f816feb61eccae8c9632e7a26253d13964bf6cd6b09dcaa47","source":{"kind":"arxiv","id":"2312.09481","version":6},"attestation_state":"computed","paper":{"title":"Continual Adversarial Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hefei Ling, Ning Yu, Qian Wang, Qihao Liu, Ruoxi Jia, Yingwei Li","submitted_at":"2023-12-15T01:38:26Z","abstract_excerpt":"In response to the rapidly evolving nature of adversarial attacks against visual classifiers, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is unrealistic, as the environment in which the defense system operates is dynamic. Over time, new attacks inevitably emerge that exploit the vulnerabilities of existing defenses and bypass them. Therefore, we propose a continual defense strategy under a practical threat model and, for the first time, introduce the Continual Adversar"},"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":"2312.09481","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T01:38:26Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"fbd07d1ce545b431a8b1bd22f6a242298921f96c2b1bdbd0fee6d2725122fe44","abstract_canon_sha256":"03a6b9dd7d4ac7cc10c470f9cd2b30eb502fcc0679a2f3949cc8df6bd1599e55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:10.705400Z","signature_b64":"kdMsucflQ0h2DHkt3fFcQkjzqqvlkDO1Vfb/X90MKfuTSnDeTRZxRS1Cn333BEMSlaSwj58Aj8B17RnOjVloDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4ea4d500cf3d11f816feb61eccae8c9632e7a26253d13964bf6cd6b09dcaa47","last_reissued_at":"2026-07-05T11:47:10.704868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:10.704868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Adversarial Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hefei Ling, Ning Yu, Qian Wang, Qihao Liu, Ruoxi Jia, Yingwei Li","submitted_at":"2023-12-15T01:38:26Z","abstract_excerpt":"In response to the rapidly evolving nature of adversarial attacks against visual classifiers, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is unrealistic, as the environment in which the defense system operates is dynamic. Over time, new attacks inevitably emerge that exploit the vulnerabilities of existing defenses and bypass them. Therefore, we propose a continual defense strategy under a practical threat model and, for the first time, introduce the Continual Adversar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09481","kind":"arxiv","version":6},"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/2312.09481/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":"2312.09481","created_at":"2026-07-05T11:47:10.704930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09481v6","created_at":"2026-07-05T11:47:10.704930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09481","created_at":"2026-07-05T11:47:10.704930+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTVE2UAM6PIR","created_at":"2026-07-05T11:47:10.704930+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTVE2UAM6PIR7ALP","created_at":"2026-07-05T11:47:10.704930+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTVE2UAM","created_at":"2026-07-05T11:47:10.704930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12655","citing_title":"Amnesia: A Stealthy Replay Attack on Continual Learning Dreams","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF","json":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF.json","graph_json":"https://pith.science/api/pith-number/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/graph.json","events_json":"https://pith.science/api/pith-number/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/events.json","paper":"https://pith.science/paper/WTVE2UAM"},"agent_actions":{"view_html":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF","download_json":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF.json","view_paper":"https://pith.science/paper/WTVE2UAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09481&json=true","fetch_graph":"https://pith.science/api/pith-number/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/graph.json","fetch_events":"https://pith.science/api/pith-number/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/action/storage_attestation","attest_author":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/action/author_attestation","sign_citation":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/action/citation_signature","submit_replication":"https://pith.science/pith/WTVE2UAM6PIR7ALP5NQ6ZSXIZF/action/replication_record"}},"created_at":"2026-07-05T11:47:10.704930+00:00","updated_at":"2026-07-05T11:47:10.704930+00:00"}