{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JOYRK35MAAUBKQ72OTX62KMDRG","short_pith_number":"pith:JOYRK35M","schema_version":"1.0","canonical_sha256":"4bb1156fac00281543fa74efed298389b88ecc9b0d905d611793bfd98eddc2f7","source":{"kind":"arxiv","id":"1901.08846","version":3},"attestation_state":"computed","paper":{"title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Du, Jun Zhu, Kun Xu, Ning Chen, Tianyu Pang","submitted_at":"2019-01-25T11:57:39Z","abstract_excerpt":"Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble, e.g., by directly averaging the outputs, which ignores the interaction among networks. This paper presents a new method that explores the interaction among individual networks to improve robustness for ensemble models. Technically, we define a new notion of ensemble diversity i"},"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":"1901.08846","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T11:57:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1dedd83faec90fe383dda8f9e0397094f5dc10b076bfb5d09cadfdd887e42db3","abstract_canon_sha256":"85f6619a636fd6092f49aa4fec3efa47b2a8e3ea6054e81b270e1855dd924c87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.654997Z","signature_b64":"+KFKQ9ik8vRzPXZs6eywFKIzEh51QCKetJol7STnmJRqpQt0cOx0q3Q9ei902YVeQEqV6rRwe9GRLttaroQgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb1156fac00281543fa74efed298389b88ecc9b0d905d611793bfd98eddc2f7","last_reissued_at":"2026-05-17T23:44:47.654397Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.654397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Du, Jun Zhu, Kun Xu, Ning Chen, Tianyu Pang","submitted_at":"2019-01-25T11:57:39Z","abstract_excerpt":"Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble, e.g., by directly averaging the outputs, which ignores the interaction among networks. This paper presents a new method that explores the interaction among individual networks to improve robustness for ensemble models. Technically, we define a new notion of ensemble diversity i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08846","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":""},"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":"1901.08846","created_at":"2026-05-17T23:44:47.654488+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08846v3","created_at":"2026-05-17T23:44:47.654488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08846","created_at":"2026-05-17T23:44:47.654488+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOYRK35MAAUB","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOYRK35MAAUBKQ72","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOYRK35M","created_at":"2026-05-18T12:33:21.387695+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/JOYRK35MAAUBKQ72OTX62KMDRG","json":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG.json","graph_json":"https://pith.science/api/pith-number/JOYRK35MAAUBKQ72OTX62KMDRG/graph.json","events_json":"https://pith.science/api/pith-number/JOYRK35MAAUBKQ72OTX62KMDRG/events.json","paper":"https://pith.science/paper/JOYRK35M"},"agent_actions":{"view_html":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG","download_json":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG.json","view_paper":"https://pith.science/paper/JOYRK35M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08846&json=true","fetch_graph":"https://pith.science/api/pith-number/JOYRK35MAAUBKQ72OTX62KMDRG/graph.json","fetch_events":"https://pith.science/api/pith-number/JOYRK35MAAUBKQ72OTX62KMDRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG/action/storage_attestation","attest_author":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG/action/author_attestation","sign_citation":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG/action/citation_signature","submit_replication":"https://pith.science/pith/JOYRK35MAAUBKQ72OTX62KMDRG/action/replication_record"}},"created_at":"2026-05-17T23:44:47.654488+00:00","updated_at":"2026-05-17T23:44:47.654488+00:00"}