{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MLAIKEITYXQKT7YLNBNS2ONVXC","short_pith_number":"pith:MLAIKEIT","schema_version":"1.0","canonical_sha256":"62c0851113c5e0a9ff0b685b2d39b5b8bb8beddb4a2210dddb6f684a2e9f480c","source":{"kind":"arxiv","id":"2006.11890","version":5},"attestation_state":"computed","paper":{"title":"Graph Backdoor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ren Pang, Shouling Ji, Ting Wang, Zhaohan Xi","submitted_at":"2020-06-21T19:45:30Z","abstract_excerpt":"One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally otherwise. Despite the plethora of prior work on DNNs for continuous data (e.g., images), the vulnerability of graph neural networks (GNNs) for discrete-structured data (e.g., graphs) is largely unexplored, which is highly concerning given their increasing use in security-sensitive domains. To bridge this gap, we present GTA, the first backdoor attack on GNNs. Compared with prio"},"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":"2006.11890","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-21T19:45:30Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"d0fee9eff9f52ade7c319141580d77dc3343b9a6d3b2ce5c70bea230f0755d29","abstract_canon_sha256":"b948724e305cdcbc3f90f2b98e5b916408b469cce55ad670bb288c98b0b02194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:16.801182Z","signature_b64":"48I098P1zNKsxoYRAm33yHWr7yqenH90Yc7VX81LWjfUktFAL6EDZapbkMcQC46iHRbvTRyYO78K+k89vFBmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c0851113c5e0a9ff0b685b2d39b5b8bb8beddb4a2210dddb6f684a2e9f480c","last_reissued_at":"2026-07-05T03:04:16.800794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:16.800794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Backdoor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ren Pang, Shouling Ji, Ting Wang, Zhaohan Xi","submitted_at":"2020-06-21T19:45:30Z","abstract_excerpt":"One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally otherwise. Despite the plethora of prior work on DNNs for continuous data (e.g., images), the vulnerability of graph neural networks (GNNs) for discrete-structured data (e.g., graphs) is largely unexplored, which is highly concerning given their increasing use in security-sensitive domains. To bridge this gap, we present GTA, the first backdoor attack on GNNs. Compared with prio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11890","kind":"arxiv","version":5},"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/2006.11890/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":"2006.11890","created_at":"2026-07-05T03:04:16.800856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11890v5","created_at":"2026-07-05T03:04:16.800856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11890","created_at":"2026-07-05T03:04:16.800856+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLAIKEITYXQK","created_at":"2026-07-05T03:04:16.800856+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLAIKEITYXQKT7YL","created_at":"2026-07-05T03:04:16.800856+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLAIKEIT","created_at":"2026-07-05T03:04:16.800856+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/MLAIKEITYXQKT7YLNBNS2ONVXC","json":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC.json","graph_json":"https://pith.science/api/pith-number/MLAIKEITYXQKT7YLNBNS2ONVXC/graph.json","events_json":"https://pith.science/api/pith-number/MLAIKEITYXQKT7YLNBNS2ONVXC/events.json","paper":"https://pith.science/paper/MLAIKEIT"},"agent_actions":{"view_html":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC","download_json":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC.json","view_paper":"https://pith.science/paper/MLAIKEIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11890&json=true","fetch_graph":"https://pith.science/api/pith-number/MLAIKEITYXQKT7YLNBNS2ONVXC/graph.json","fetch_events":"https://pith.science/api/pith-number/MLAIKEITYXQKT7YLNBNS2ONVXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC/action/storage_attestation","attest_author":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC/action/author_attestation","sign_citation":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC/action/citation_signature","submit_replication":"https://pith.science/pith/MLAIKEITYXQKT7YLNBNS2ONVXC/action/replication_record"}},"created_at":"2026-07-05T03:04:16.800856+00:00","updated_at":"2026-07-05T03:04:16.800856+00:00"}