{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CS6L4UVJOMLFDC7HAWJK6JKLNU","short_pith_number":"pith:CS6L4UVJ","schema_version":"1.0","canonical_sha256":"14bcbe52a97316518be70592af254b6d17c4bee33a3810481ccf397b762ddf00","source":{"kind":"arxiv","id":"2108.06280","version":2},"attestation_state":"computed","paper":{"title":"Understanding Structural Vulnerability in Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Jintang Li, Liang Chen, Qibiao Peng, Yang Liu, Zibin Zheng","submitted_at":"2021-08-13T15:07:44Z","abstract_excerpt":"Recent studies have shown that Graph Convolutional Networks (GCNs) are vulnerable to adversarial attacks on the graph structure. Although multiple works have been proposed to improve their robustness against such structural adversarial attacks, the reasons for the success of the attacks remain unclear. In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i.e., the weighted mean) of GCNs. Specifically, our analysis takes advantage of the breakdown point which can quantitatively measure the robustn"},"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":"2108.06280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-13T15:07:44Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"8ea3fc1e09570d9a9fbc038f45b197def2af4546a8d2dd395e8c37e1e7e02e5a","abstract_canon_sha256":"422883a44fc2184ae8b898d01a965cfd322fdb6c063a7134fcb3b56ce9584fc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:31.803101Z","signature_b64":"souDUnegcDo9NE7grlRHC8EMF+A98rhHxq/iobwMoX5qNRneQ6Zc5blRmZRhbwjezl1VVYmksru44WQqIemhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14bcbe52a97316518be70592af254b6d17c4bee33a3810481ccf397b762ddf00","last_reissued_at":"2026-07-05T03:13:31.802731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:31.802731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Structural Vulnerability in Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Jintang Li, Liang Chen, Qibiao Peng, Yang Liu, Zibin Zheng","submitted_at":"2021-08-13T15:07:44Z","abstract_excerpt":"Recent studies have shown that Graph Convolutional Networks (GCNs) are vulnerable to adversarial attacks on the graph structure. Although multiple works have been proposed to improve their robustness against such structural adversarial attacks, the reasons for the success of the attacks remain unclear. In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i.e., the weighted mean) of GCNs. Specifically, our analysis takes advantage of the breakdown point which can quantitatively measure the robustn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06280","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.06280/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":"2108.06280","created_at":"2026-07-05T03:13:31.802793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06280v2","created_at":"2026-07-05T03:13:31.802793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06280","created_at":"2026-07-05T03:13:31.802793+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS6L4UVJOMLF","created_at":"2026-07-05T03:13:31.802793+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS6L4UVJOMLFDC7H","created_at":"2026-07-05T03:13:31.802793+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS6L4UVJ","created_at":"2026-07-05T03:13:31.802793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05883","citing_title":"On the Adversarial Robustness of Graph Neural Networks with Graph Reduction","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU","json":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU.json","graph_json":"https://pith.science/api/pith-number/CS6L4UVJOMLFDC7HAWJK6JKLNU/graph.json","events_json":"https://pith.science/api/pith-number/CS6L4UVJOMLFDC7HAWJK6JKLNU/events.json","paper":"https://pith.science/paper/CS6L4UVJ"},"agent_actions":{"view_html":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU","download_json":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU.json","view_paper":"https://pith.science/paper/CS6L4UVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06280&json=true","fetch_graph":"https://pith.science/api/pith-number/CS6L4UVJOMLFDC7HAWJK6JKLNU/graph.json","fetch_events":"https://pith.science/api/pith-number/CS6L4UVJOMLFDC7HAWJK6JKLNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU/action/storage_attestation","attest_author":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU/action/author_attestation","sign_citation":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU/action/citation_signature","submit_replication":"https://pith.science/pith/CS6L4UVJOMLFDC7HAWJK6JKLNU/action/replication_record"}},"created_at":"2026-07-05T03:13:31.802793+00:00","updated_at":"2026-07-05T03:13:31.802793+00:00"}