{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PBNKYAZO2EAIYYQFWC6C5UI2M4","short_pith_number":"pith:PBNKYAZO","schema_version":"1.0","canonical_sha256":"785aac032ed1008c6205b0bc2ed11a671dee83d92a2988556fb821751d851325","source":{"kind":"arxiv","id":"2506.00191","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Graph Backdoor Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daniel Takabi, Jiawei Chen, Lusi Li, Masha Sosonkina, Rui Ning","submitted_at":"2025-05-30T20:02:43Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplored. To address this gap, we conduct the first investigation into the susceptibility of HGNNs to existing graph backdoor attacks, revealing three critical issues: (1) high attack budget required for effective backdoor injection, (2) inefficient and unreliable backdoor activation, and (3) inaccurate attack effectiveness evaluation. To tackle these issues, we propose the Heterogeneous Graph Backdoor Attack (HGBA), the "},"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":"2506.00191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-30T20:02:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"563090a710e2d9d119cc574e41ff60b46546e0caa213a1ba7e90872a1f82d16d","abstract_canon_sha256":"9b3c5b6c09b96b9f7d2f6d22b363f441f35e940903e3c11b9f306af55597cf7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:30.451443Z","signature_b64":"PhmQlf2h+y+Ad003UBgcgja5qKLJzOgi3/EzVnyuVyESro1VI3Bp3Wfi9voCmHAsVaAKYsL083JvR4sQf7pzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785aac032ed1008c6205b0bc2ed11a671dee83d92a2988556fb821751d851325","last_reissued_at":"2026-07-05T11:13:30.451019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:30.451019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Graph Backdoor Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daniel Takabi, Jiawei Chen, Lusi Li, Masha Sosonkina, Rui Ning","submitted_at":"2025-05-30T20:02:43Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplored. To address this gap, we conduct the first investigation into the susceptibility of HGNNs to existing graph backdoor attacks, revealing three critical issues: (1) high attack budget required for effective backdoor injection, (2) inefficient and unreliable backdoor activation, and (3) inaccurate attack effectiveness evaluation. To tackle these issues, we propose the Heterogeneous Graph Backdoor Attack (HGBA), the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00191","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/2506.00191/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":"2506.00191","created_at":"2026-07-05T11:13:30.451072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00191v1","created_at":"2026-07-05T11:13:30.451072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00191","created_at":"2026-07-05T11:13:30.451072+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBNKYAZO2EAI","created_at":"2026-07-05T11:13:30.451072+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBNKYAZO2EAIYYQF","created_at":"2026-07-05T11:13:30.451072+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBNKYAZO","created_at":"2026-07-05T11:13:30.451072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12919","citing_title":"Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4","json":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4.json","graph_json":"https://pith.science/api/pith-number/PBNKYAZO2EAIYYQFWC6C5UI2M4/graph.json","events_json":"https://pith.science/api/pith-number/PBNKYAZO2EAIYYQFWC6C5UI2M4/events.json","paper":"https://pith.science/paper/PBNKYAZO"},"agent_actions":{"view_html":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4","download_json":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4.json","view_paper":"https://pith.science/paper/PBNKYAZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00191&json=true","fetch_graph":"https://pith.science/api/pith-number/PBNKYAZO2EAIYYQFWC6C5UI2M4/graph.json","fetch_events":"https://pith.science/api/pith-number/PBNKYAZO2EAIYYQFWC6C5UI2M4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4/action/storage_attestation","attest_author":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4/action/author_attestation","sign_citation":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4/action/citation_signature","submit_replication":"https://pith.science/pith/PBNKYAZO2EAIYYQFWC6C5UI2M4/action/replication_record"}},"created_at":"2026-07-05T11:13:30.451072+00:00","updated_at":"2026-07-05T11:13:30.451072+00:00"}