{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FPYOOHYVQN7XFMPM4L5U3BMZBA","short_pith_number":"pith:FPYOOHYV","schema_version":"1.0","canonical_sha256":"2bf0e71f15837f72b1ece2fb4d8599080773ad814c1ce094d9adb34aee090f97","source":{"kind":"arxiv","id":"2401.09945","version":1},"attestation_state":"computed","paper":{"title":"HGAttack: Transferable Heterogeneous Graph Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IR"],"primary_cat":"cs.LG","authors_text":"Chunyan Miao, Deheng Ye, He Zhao, Yongwei Wang, Zhiwei Zeng","submitted_at":"2024-01-18T12:47:13Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which are primarily designed for homogeneous graphs, fall short when applied to HGNNs due to their limited ability to address the structural and semantic complexity of HGNNs. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs. We design a novel surrogate model to closely resemble the behaviors of the target"},"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":"2401.09945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T12:47:13Z","cross_cats_sorted":["cs.CR","cs.IR"],"title_canon_sha256":"652dce878cafe4c7f8d5e75fbc778dd2bf1427eff6cd0f5b96f394c48c20127a","abstract_canon_sha256":"b62baacb97d92297b8c6e2c81dd56bb76fee9a30db803cd1a2d46e9359d06949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:04.569193Z","signature_b64":"5kTOB8hSgBQl0l7Mm/5I1W3wfIT827Zedof71PtDIaRYIU87noFgMFtaidxv4iHRJXfcScGYfdhjRMeFq7JjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf0e71f15837f72b1ece2fb4d8599080773ad814c1ce094d9adb34aee090f97","last_reissued_at":"2026-07-05T07:35:04.568771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:04.568771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HGAttack: Transferable Heterogeneous Graph Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IR"],"primary_cat":"cs.LG","authors_text":"Chunyan Miao, Deheng Ye, He Zhao, Yongwei Wang, Zhiwei Zeng","submitted_at":"2024-01-18T12:47:13Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which are primarily designed for homogeneous graphs, fall short when applied to HGNNs due to their limited ability to address the structural and semantic complexity of HGNNs. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs. We design a novel surrogate model to closely resemble the behaviors of the target"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09945","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/2401.09945/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":"2401.09945","created_at":"2026-07-05T07:35:04.568838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09945v1","created_at":"2026-07-05T07:35:04.568838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09945","created_at":"2026-07-05T07:35:04.568838+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPYOOHYVQN7X","created_at":"2026-07-05T07:35:04.568838+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPYOOHYVQN7XFMPM","created_at":"2026-07-05T07:35:04.568838+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPYOOHYV","created_at":"2026-07-05T07:35:04.568838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07428","citing_title":"HeTa: Relation-wise Heterogeneous Graph Foundation Attack Model","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA","json":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA.json","graph_json":"https://pith.science/api/pith-number/FPYOOHYVQN7XFMPM4L5U3BMZBA/graph.json","events_json":"https://pith.science/api/pith-number/FPYOOHYVQN7XFMPM4L5U3BMZBA/events.json","paper":"https://pith.science/paper/FPYOOHYV"},"agent_actions":{"view_html":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA","download_json":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA.json","view_paper":"https://pith.science/paper/FPYOOHYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09945&json=true","fetch_graph":"https://pith.science/api/pith-number/FPYOOHYVQN7XFMPM4L5U3BMZBA/graph.json","fetch_events":"https://pith.science/api/pith-number/FPYOOHYVQN7XFMPM4L5U3BMZBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA/action/storage_attestation","attest_author":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA/action/author_attestation","sign_citation":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA/action/citation_signature","submit_replication":"https://pith.science/pith/FPYOOHYVQN7XFMPM4L5U3BMZBA/action/replication_record"}},"created_at":"2026-07-05T07:35:04.568838+00:00","updated_at":"2026-07-05T07:35:04.568838+00:00"}