{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:75JZ7XEMQEBSNGQ267ITZFNV25","short_pith_number":"pith:75JZ7XEM","schema_version":"1.0","canonical_sha256":"ff539fdc8c8103269a1af7d13c95b5d7429ff3746c120f484f1b94090148f1c6","source":{"kind":"arxiv","id":"1906.12269","version":1},"attestation_state":"computed","paper":{"title":"Certifiable Robustness and Robust Training for Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Z\\\"ugner, Stephan G\\\"unnemann","submitted_at":"2019-06-28T15:40:10Z","abstract_excerpt":"Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable (non-)robustness of graph convolutional networks with respect to perturbations of the node attributes. We consider the case of binary node attributes (e.g. bag-of-words) and perturbations that are L_0-bounded. If a node has been certified with our method, it is guaranteed to be robust under any possible perturbation given the attack model. Likewise, we can "},"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":"1906.12269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-28T15:40:10Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"f2aef535bed3cccb1579cda2a3d01ce246837a6c8b4fc8f7a0187aaf9412ec6f","abstract_canon_sha256":"54660fb9fa77ff2ebe44374b9153aa8451ee69fd975e74568ca99f67b9193ffe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:58.810536Z","signature_b64":"8pe59G7Pfrnczq5EWlcH5CCFFm+TNWLqBQFBygqlivF9hRoEFPwLXi0k+2wp1/KMNkqdFfBOT3lHQKUAqL3pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff539fdc8c8103269a1af7d13c95b5d7429ff3746c120f484f1b94090148f1c6","last_reissued_at":"2026-05-17T23:41:58.810024Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:58.810024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certifiable Robustness and Robust Training for Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Z\\\"ugner, Stephan G\\\"unnemann","submitted_at":"2019-06-28T15:40:10Z","abstract_excerpt":"Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable (non-)robustness of graph convolutional networks with respect to perturbations of the node attributes. We consider the case of binary node attributes (e.g. bag-of-words) and perturbations that are L_0-bounded. If a node has been certified with our method, it is guaranteed to be robust under any possible perturbation given the attack model. Likewise, we can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12269","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":""},"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":"1906.12269","created_at":"2026-05-17T23:41:58.810113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12269v1","created_at":"2026-05-17T23:41:58.810113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12269","created_at":"2026-05-17T23:41:58.810113+00:00"},{"alias_kind":"pith_short_12","alias_value":"75JZ7XEMQEBS","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"75JZ7XEMQEBSNGQ2","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"75JZ7XEM","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/75JZ7XEMQEBSNGQ267ITZFNV25","json":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25.json","graph_json":"https://pith.science/api/pith-number/75JZ7XEMQEBSNGQ267ITZFNV25/graph.json","events_json":"https://pith.science/api/pith-number/75JZ7XEMQEBSNGQ267ITZFNV25/events.json","paper":"https://pith.science/paper/75JZ7XEM"},"agent_actions":{"view_html":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25","download_json":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25.json","view_paper":"https://pith.science/paper/75JZ7XEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12269&json=true","fetch_graph":"https://pith.science/api/pith-number/75JZ7XEMQEBSNGQ267ITZFNV25/graph.json","fetch_events":"https://pith.science/api/pith-number/75JZ7XEMQEBSNGQ267ITZFNV25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25/action/storage_attestation","attest_author":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25/action/author_attestation","sign_citation":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25/action/citation_signature","submit_replication":"https://pith.science/pith/75JZ7XEMQEBSNGQ267ITZFNV25/action/replication_record"}},"created_at":"2026-05-17T23:41:58.810113+00:00","updated_at":"2026-05-17T23:41:58.810113+00:00"}