{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A3OTBZQW5V3M4BSEWDNN2A5PMB","short_pith_number":"pith:A3OTBZQW","schema_version":"1.0","canonical_sha256":"06dd30e616ed76ce0644b0dadd03af605eb979258993bbc8355aee81d38c70fc","source":{"kind":"arxiv","id":"1905.03679","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Defense Framework for Graph Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haifeng Chen, Jingchao Ni, Philip S. Yu, Shen Wang, Xiao Yu, Zhengzhang Chen, Zhichun Li","submitted_at":"2019-05-09T15:10:30Z","abstract_excerpt":"Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities and defense GNN against the adversarial attacks? In this paper, we propose DefNet, an effective adversarial defense framework for GNNs. In particular, we first investigate the latent vulnerabilities in every layer of GNNs and propose corresponding strategies including dual-stage "},"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":"1905.03679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T15:10:30Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"9c23091eaa40ef03ec6776c0e5a24e9bc24f95554571a7d1f5168f1a93dd17c6","abstract_canon_sha256":"3af7a1fb071039e70166291850e549c184b40f49ef0a8c6867ce9723192a9f27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:25.456336Z","signature_b64":"/eFWaoVV+LONw06vqzpW0rKYYo5ug864mF+BB09fK0rA/fJfuKQetLsSXnLSfNaYzQw4jpyBq+uWFJn4TQrpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06dd30e616ed76ce0644b0dadd03af605eb979258993bbc8355aee81d38c70fc","last_reissued_at":"2026-05-17T23:46:25.455776Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:25.455776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Defense Framework for Graph Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haifeng Chen, Jingchao Ni, Philip S. Yu, Shen Wang, Xiao Yu, Zhengzhang Chen, Zhichun Li","submitted_at":"2019-05-09T15:10:30Z","abstract_excerpt":"Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities and defense GNN against the adversarial attacks? In this paper, we propose DefNet, an effective adversarial defense framework for GNNs. In particular, we first investigate the latent vulnerabilities in every layer of GNNs and propose corresponding strategies including dual-stage "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03679","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":""},"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":"1905.03679","created_at":"2026-05-17T23:46:25.455879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03679v2","created_at":"2026-05-17T23:46:25.455879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03679","created_at":"2026-05-17T23:46:25.455879+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3OTBZQW5V3M","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3OTBZQW5V3M4BSE","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3OTBZQW","created_at":"2026-05-18T12:33:12.712433+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/A3OTBZQW5V3M4BSEWDNN2A5PMB","json":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB.json","graph_json":"https://pith.science/api/pith-number/A3OTBZQW5V3M4BSEWDNN2A5PMB/graph.json","events_json":"https://pith.science/api/pith-number/A3OTBZQW5V3M4BSEWDNN2A5PMB/events.json","paper":"https://pith.science/paper/A3OTBZQW"},"agent_actions":{"view_html":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB","download_json":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB.json","view_paper":"https://pith.science/paper/A3OTBZQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03679&json=true","fetch_graph":"https://pith.science/api/pith-number/A3OTBZQW5V3M4BSEWDNN2A5PMB/graph.json","fetch_events":"https://pith.science/api/pith-number/A3OTBZQW5V3M4BSEWDNN2A5PMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB/action/storage_attestation","attest_author":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB/action/author_attestation","sign_citation":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB/action/citation_signature","submit_replication":"https://pith.science/pith/A3OTBZQW5V3M4BSEWDNN2A5PMB/action/replication_record"}},"created_at":"2026-05-17T23:46:25.455879+00:00","updated_at":"2026-05-17T23:46:25.455879+00:00"}