{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QOW342EOL3QT36Z4WVAMR22I7L","short_pith_number":"pith:QOW342EO","schema_version":"1.0","canonical_sha256":"83adbe688e5ee13dfb3cb540c8eb48fafe02363d4ba491ea642ba89631ff7096","source":{"kind":"arxiv","id":"2111.00684","version":3},"attestation_state":"computed","paper":{"title":"Graph Structural Attack by Perturbing Spectral Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Ethan Blaser, Hongning Wang, Lu Lin","submitted_at":"2021-11-01T04:02:34Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) have fueled a surge of research interest due to their encouraging performance on graph learning tasks, but they are also shown vulnerability to adversarial attacks. In this paper, an effective graph structural attack is investigated to disrupt graph spectral filters in the Fourier domain, which are the theoretical foundation of GCNs. We define the notion of spectral distance based on the eigenvalues of graph Laplacian to measure the disruption of spectral filters. We realize the attack by maximizing the spectral distance and propose an efficient approximatio"},"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":"2111.00684","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T04:02:34Z","cross_cats_sorted":["cs.AI","cs.CR","cs.SI"],"title_canon_sha256":"50a63b65c980b385be569fa3676a2a4a50717c7770f7c7b1a23f93577e35cafb","abstract_canon_sha256":"f2c342aad8cf643fb0fd9f58c066b15cf1e6c313880f33f2569e1390d6ae12f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:39.784577Z","signature_b64":"zFvTHfzwjbETwhUfZDMaPR0jtYQFDE6lEM8uMsou3X/h6NPWcEd+5SNEn/Yk8i5L+dq+8DjhzugIxep+VHX8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83adbe688e5ee13dfb3cb540c8eb48fafe02363d4ba491ea642ba89631ff7096","last_reissued_at":"2026-07-05T05:02:39.784208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:39.784208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Structural Attack by Perturbing Spectral Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Ethan Blaser, Hongning Wang, Lu Lin","submitted_at":"2021-11-01T04:02:34Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) have fueled a surge of research interest due to their encouraging performance on graph learning tasks, but they are also shown vulnerability to adversarial attacks. In this paper, an effective graph structural attack is investigated to disrupt graph spectral filters in the Fourier domain, which are the theoretical foundation of GCNs. We define the notion of spectral distance based on the eigenvalues of graph Laplacian to measure the disruption of spectral filters. We realize the attack by maximizing the spectral distance and propose an efficient approximatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00684","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.00684/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":"2111.00684","created_at":"2026-07-05T05:02:39.784261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00684v3","created_at":"2026-07-05T05:02:39.784261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00684","created_at":"2026-07-05T05:02:39.784261+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOW342EOL3QT","created_at":"2026-07-05T05:02:39.784261+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOW342EOL3QT36Z4","created_at":"2026-07-05T05:02:39.784261+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOW342EO","created_at":"2026-07-05T05:02:39.784261+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/QOW342EOL3QT36Z4WVAMR22I7L","json":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L.json","graph_json":"https://pith.science/api/pith-number/QOW342EOL3QT36Z4WVAMR22I7L/graph.json","events_json":"https://pith.science/api/pith-number/QOW342EOL3QT36Z4WVAMR22I7L/events.json","paper":"https://pith.science/paper/QOW342EO"},"agent_actions":{"view_html":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L","download_json":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L.json","view_paper":"https://pith.science/paper/QOW342EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00684&json=true","fetch_graph":"https://pith.science/api/pith-number/QOW342EOL3QT36Z4WVAMR22I7L/graph.json","fetch_events":"https://pith.science/api/pith-number/QOW342EOL3QT36Z4WVAMR22I7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L/action/storage_attestation","attest_author":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L/action/author_attestation","sign_citation":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L/action/citation_signature","submit_replication":"https://pith.science/pith/QOW342EOL3QT36Z4WVAMR22I7L/action/replication_record"}},"created_at":"2026-07-05T05:02:39.784261+00:00","updated_at":"2026-07-05T05:02:39.784261+00:00"}