{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MLI4Q3Q3KADUYVA7LRFKXOVPO3","short_pith_number":"pith:MLI4Q3Q3","schema_version":"1.0","canonical_sha256":"62d1c86e1b50074c541f5c4aabbaaf76e0da5edcff3e98ffb711019ba52fbbdf","source":{"kind":"arxiv","id":"2311.17608","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Robust Memory-Based Continual Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Danding Wang, Fan Tang, Juan Cao, Peng Li, Xiaoyue Mi, Yang Liu, Zonghan Yang","submitted_at":"2023-11-29T13:05:20Z","abstract_excerpt":"Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed. We delve into the adversarial robustness of memory-based continual learning algorithms and observe limited robustness improvement by directly applying adversarial training techniques. Preliminary studies reveal the twin challenges for building adversarial robust continual learners: accelerated forgetting in continual learning and gradient obfuscation in adversarial robustness. In this study, we put forward a novel adversarial robust memory-based"},"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":"2311.17608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T13:05:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d3752466e7c930b931a5ce7a1c7158660afebe474cb61b5747a000dc9cec2b7","abstract_canon_sha256":"2b274d5fb21a930986e6ac8d9088fc059c23d090f04bdc0cd079083085c5794c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:16.159226Z","signature_b64":"LaVn+ITwXEIUjubaFLUUd7+pKQMDZZMrbvguxQXeBd5Ft3TjE6y3AoZ27pdT+oNanOso6dZ07yaXRztT6cPNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62d1c86e1b50074c541f5c4aabbaaf76e0da5edcff3e98ffb711019ba52fbbdf","last_reissued_at":"2026-07-05T07:18:16.158817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:16.158817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Robust Memory-Based Continual Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Danding Wang, Fan Tang, Juan Cao, Peng Li, Xiaoyue Mi, Yang Liu, Zonghan Yang","submitted_at":"2023-11-29T13:05:20Z","abstract_excerpt":"Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed. We delve into the adversarial robustness of memory-based continual learning algorithms and observe limited robustness improvement by directly applying adversarial training techniques. Preliminary studies reveal the twin challenges for building adversarial robust continual learners: accelerated forgetting in continual learning and gradient obfuscation in adversarial robustness. In this study, we put forward a novel adversarial robust memory-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17608","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/2311.17608/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":"2311.17608","created_at":"2026-07-05T07:18:16.158875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17608v1","created_at":"2026-07-05T07:18:16.158875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17608","created_at":"2026-07-05T07:18:16.158875+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLI4Q3Q3KADU","created_at":"2026-07-05T07:18:16.158875+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLI4Q3Q3KADUYVA7","created_at":"2026-07-05T07:18:16.158875+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLI4Q3Q3","created_at":"2026-07-05T07:18:16.158875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29841","citing_title":"Theory of Continual Learning Against Data Poisoning Attacks","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3","json":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3.json","graph_json":"https://pith.science/api/pith-number/MLI4Q3Q3KADUYVA7LRFKXOVPO3/graph.json","events_json":"https://pith.science/api/pith-number/MLI4Q3Q3KADUYVA7LRFKXOVPO3/events.json","paper":"https://pith.science/paper/MLI4Q3Q3"},"agent_actions":{"view_html":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3","download_json":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3.json","view_paper":"https://pith.science/paper/MLI4Q3Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17608&json=true","fetch_graph":"https://pith.science/api/pith-number/MLI4Q3Q3KADUYVA7LRFKXOVPO3/graph.json","fetch_events":"https://pith.science/api/pith-number/MLI4Q3Q3KADUYVA7LRFKXOVPO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3/action/storage_attestation","attest_author":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3/action/author_attestation","sign_citation":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3/action/citation_signature","submit_replication":"https://pith.science/pith/MLI4Q3Q3KADUYVA7LRFKXOVPO3/action/replication_record"}},"created_at":"2026-07-05T07:18:16.158875+00:00","updated_at":"2026-07-05T07:18:16.158875+00:00"}