{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CR2IMPFQYZT2LKDHVUFGK7K2L7","short_pith_number":"pith:CR2IMPFQ","schema_version":"1.0","canonical_sha256":"1474863cb0c667a5a867ad0a657d5a5fcb7817a10c8139c2962d91039ba9be1c","source":{"kind":"arxiv","id":"2606.29240","version":1},"attestation_state":"computed","paper":{"title":"Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Gaoxi Xiao, Honglin Gao, Jindong Chang, Junhao Ren, Lan Zhao, Yue Yang","submitted_at":"2026-06-28T07:11:05Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types. However, their robustness under realistic black-box adversarial settings remains insufficiently explored. Existing attacks on HGNNs usually assume access to model gradients, soft prediction scores, or the complete graph structure, which is often unavailable when HGNN-based services are deployed as closed systems. In this paper, we propose Blackknife, a hard-label, query-limited, and structure-limited black-box evasion attack framework for"},"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":"2606.29240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T07:11:05Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"aeb14f00a5868bf52c795d8cf9660f87362a568a9e41cce409e54c76862d9ef0","abstract_canon_sha256":"611fd092dd9a82505e085f7bb9f130518a54ae35c589d883475f67e5b9859edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:58.619968Z","signature_b64":"qbKCKb+DAKb7vnfABPjnGOR1Rtyu95t9OLdZ3lGLorslD10De4ZW8tI6OCKcURxhmCj0G06W8IlL4SUmpwVwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1474863cb0c667a5a867ad0a657d5a5fcb7817a10c8139c2962d91039ba9be1c","last_reissued_at":"2026-06-30T01:17:58.619470Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:58.619470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Gaoxi Xiao, Honglin Gao, Jindong Chang, Junhao Ren, Lan Zhao, Yue Yang","submitted_at":"2026-06-28T07:11:05Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types. However, their robustness under realistic black-box adversarial settings remains insufficiently explored. Existing attacks on HGNNs usually assume access to model gradients, soft prediction scores, or the complete graph structure, which is often unavailable when HGNN-based services are deployed as closed systems. In this paper, we propose Blackknife, a hard-label, query-limited, and structure-limited black-box evasion attack framework for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29240","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/2606.29240/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":"2606.29240","created_at":"2026-06-30T01:17:58.619539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29240v1","created_at":"2026-06-30T01:17:58.619539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29240","created_at":"2026-06-30T01:17:58.619539+00:00"},{"alias_kind":"pith_short_12","alias_value":"CR2IMPFQYZT2","created_at":"2026-06-30T01:17:58.619539+00:00"},{"alias_kind":"pith_short_16","alias_value":"CR2IMPFQYZT2LKDH","created_at":"2026-06-30T01:17:58.619539+00:00"},{"alias_kind":"pith_short_8","alias_value":"CR2IMPFQ","created_at":"2026-06-30T01:17:58.619539+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/CR2IMPFQYZT2LKDHVUFGK7K2L7","json":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7.json","graph_json":"https://pith.science/api/pith-number/CR2IMPFQYZT2LKDHVUFGK7K2L7/graph.json","events_json":"https://pith.science/api/pith-number/CR2IMPFQYZT2LKDHVUFGK7K2L7/events.json","paper":"https://pith.science/paper/CR2IMPFQ"},"agent_actions":{"view_html":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7","download_json":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7.json","view_paper":"https://pith.science/paper/CR2IMPFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29240&json=true","fetch_graph":"https://pith.science/api/pith-number/CR2IMPFQYZT2LKDHVUFGK7K2L7/graph.json","fetch_events":"https://pith.science/api/pith-number/CR2IMPFQYZT2LKDHVUFGK7K2L7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7/action/storage_attestation","attest_author":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7/action/author_attestation","sign_citation":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7/action/citation_signature","submit_replication":"https://pith.science/pith/CR2IMPFQYZT2LKDHVUFGK7K2L7/action/replication_record"}},"created_at":"2026-06-30T01:17:58.619539+00:00","updated_at":"2026-06-30T01:17:58.619539+00:00"}