{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2QLKHLJZMAUQBXKWL2HBYBVVP","short_pith_number":"pith:L2QLKHLJ","schema_version":"1.0","canonical_sha256":"5ea0b51d69cb014806eab2f470e035abd9893409ca2ffa3a3300beaccb355908","source":{"kind":"arxiv","id":"2505.21140","version":1},"attestation_state":"computed","paper":{"title":"HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaoxi Xiao, Honglin Gao, Lan Zhao, Xiang Li","submitted_at":"2025-05-27T12:51:48Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and social networks. While existing research has been largely focused on enhancing HGNNs' predictive performance, their robustness and security, especially under backdoor attacks, remain underexplored. In this paper, we propose a novel Heterogeneous Backdoor Attack (HeteroBA) framework for node classification tasks on heterogeneous graphs. HeteroBA inserts carefully crafted trigger nodes with realistic features and targeted "},"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":"2505.21140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T12:51:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b73be57bd82e9b39d4f3f70a66a377cc2b122c7aa98544fc5387f986bb4b7774","abstract_canon_sha256":"4374cbb867cb1d68da7e673479085bdf9c86be70faa079acb70c209f8f7c5aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:24.290537Z","signature_b64":"7PsGUMNHd1+RrzMy/kYmhYeHRMDywHE17Ec9e/e28J/KKZrzQjfpRZMypMPoMWxgkIReVuMCG+5wwNA0rPwjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea0b51d69cb014806eab2f470e035abd9893409ca2ffa3a3300beaccb355908","last_reissued_at":"2026-07-05T11:10:24.290090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:24.290090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaoxi Xiao, Honglin Gao, Lan Zhao, Xiang Li","submitted_at":"2025-05-27T12:51:48Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and social networks. While existing research has been largely focused on enhancing HGNNs' predictive performance, their robustness and security, especially under backdoor attacks, remain underexplored. In this paper, we propose a novel Heterogeneous Backdoor Attack (HeteroBA) framework for node classification tasks on heterogeneous graphs. HeteroBA inserts carefully crafted trigger nodes with realistic features and targeted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21140","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.21140/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":"2505.21140","created_at":"2026-07-05T11:10:24.290145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21140v1","created_at":"2026-07-05T11:10:24.290145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21140","created_at":"2026-07-05T11:10:24.290145+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2QLKHLJZMAU","created_at":"2026-07-05T11:10:24.290145+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2QLKHLJZMAUQBXK","created_at":"2026-07-05T11:10:24.290145+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2QLKHLJ","created_at":"2026-07-05T11:10:24.290145+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/L2QLKHLJZMAUQBXKWL2HBYBVVP","json":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP.json","graph_json":"https://pith.science/api/pith-number/L2QLKHLJZMAUQBXKWL2HBYBVVP/graph.json","events_json":"https://pith.science/api/pith-number/L2QLKHLJZMAUQBXKWL2HBYBVVP/events.json","paper":"https://pith.science/paper/L2QLKHLJ"},"agent_actions":{"view_html":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP","download_json":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP.json","view_paper":"https://pith.science/paper/L2QLKHLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21140&json=true","fetch_graph":"https://pith.science/api/pith-number/L2QLKHLJZMAUQBXKWL2HBYBVVP/graph.json","fetch_events":"https://pith.science/api/pith-number/L2QLKHLJZMAUQBXKWL2HBYBVVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP/action/storage_attestation","attest_author":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP/action/author_attestation","sign_citation":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP/action/citation_signature","submit_replication":"https://pith.science/pith/L2QLKHLJZMAUQBXKWL2HBYBVVP/action/replication_record"}},"created_at":"2026-07-05T11:10:24.290145+00:00","updated_at":"2026-07-05T11:10:24.290145+00:00"}