{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QRKVCYLJQ7N3TE7QHWFFMWH5OG","short_pith_number":"pith:QRKVCYLJ","schema_version":"1.0","canonical_sha256":"845551616987dbb993f03d8a5658fd71b53e29178e031a34369dbf26688695c8","source":{"kind":"arxiv","id":"1903.01610","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Examples on Graph Data: Deep Insights into Attack and Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Docherty, Chen Wang, Huijun Wu, Kai Lu, Liming Zhu, Yuriy Tyshetskiy","submitted_at":"2019-03-05T00:43:48Z","abstract_excerpt":"Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and different definitions of imperceptible perturbations bring unique challenges and opportunities for the adversarial attacks and defenses for graph data. In this paper, we propose both attack and defense techniques. For attack, we show that the discreteness problem could easily be reso"},"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":"1903.01610","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T00:43:48Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"fd9100cdec548323a0dedc670a9dca42abd81b1f171f2b71061aa94dda02154e","abstract_canon_sha256":"2ea7266f64799b28415f3e7cef6bee1994b35b140f527f24581e5085223afbaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:25.771599Z","signature_b64":"xLSIm+vp8M0988pskzhqB4g0aAUv18chmt70j4ITfHe/WQeoIqkUxBSH+6wev6NgEroI51xxGGYAp1XWuxoDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"845551616987dbb993f03d8a5658fd71b53e29178e031a34369dbf26688695c8","last_reissued_at":"2026-05-17T23:45:25.771117Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:25.771117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Examples on Graph Data: Deep Insights into Attack and Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Docherty, Chen Wang, Huijun Wu, Kai Lu, Liming Zhu, Yuriy Tyshetskiy","submitted_at":"2019-03-05T00:43:48Z","abstract_excerpt":"Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and different definitions of imperceptible perturbations bring unique challenges and opportunities for the adversarial attacks and defenses for graph data. In this paper, we propose both attack and defense techniques. For attack, we show that the discreteness problem could easily be reso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01610","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":"1903.01610","created_at":"2026-05-17T23:45:25.771185+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.01610v3","created_at":"2026-05-17T23:45:25.771185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01610","created_at":"2026-05-17T23:45:25.771185+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRKVCYLJQ7N3","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRKVCYLJQ7N3TE7Q","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRKVCYLJ","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11568","citing_title":"Graph Defense Diffusion Model","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15370","citing_title":"TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG","json":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG.json","graph_json":"https://pith.science/api/pith-number/QRKVCYLJQ7N3TE7QHWFFMWH5OG/graph.json","events_json":"https://pith.science/api/pith-number/QRKVCYLJQ7N3TE7QHWFFMWH5OG/events.json","paper":"https://pith.science/paper/QRKVCYLJ"},"agent_actions":{"view_html":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG","download_json":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG.json","view_paper":"https://pith.science/paper/QRKVCYLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.01610&json=true","fetch_graph":"https://pith.science/api/pith-number/QRKVCYLJQ7N3TE7QHWFFMWH5OG/graph.json","fetch_events":"https://pith.science/api/pith-number/QRKVCYLJQ7N3TE7QHWFFMWH5OG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG/action/storage_attestation","attest_author":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG/action/author_attestation","sign_citation":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG/action/citation_signature","submit_replication":"https://pith.science/pith/QRKVCYLJQ7N3TE7QHWFFMWH5OG/action/replication_record"}},"created_at":"2026-05-17T23:45:25.771185+00:00","updated_at":"2026-05-17T23:45:25.771185+00:00"}