{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PH3WTNU7QSAGXKLAC5734LHHAR","short_pith_number":"pith:PH3WTNU7","schema_version":"1.0","canonical_sha256":"79f769b69f84806ba960177fbe2ce704704a6565aa732b5a43d5200f8ca23529","source":{"kind":"arxiv","id":"2508.19641","version":1},"attestation_state":"computed","paper":{"title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Bolin Shen, Chenxi Zhao, Kaixiang Zhao, Lincan Li, Shirui Pan, Yushun Dong, Yuxiang Sun","submitted_at":"2025-08-27T07:37:52Z","abstract_excerpt":"Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art graph machine learning (GML) models have become increasingly resource-intensive, turning these models and data into invaluable Intellectual Property (IP). To address the resource-intensive nature of model training, graph-based Machine-Learning-as-a-Service (GMLaaS) has emerged as an efficient solution by leveraging third-party cloud services for model development and management. However, deploying such models in GMLaaS a"},"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":"2508.19641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-27T07:37:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8128e46612363c77286ba874e5701ef723f59df038065999396131712a97d9c2","abstract_canon_sha256":"22a2331befec2ed227420dad93ab5f52655a4c1bcb6f506bd0d597cc0b3f9526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:15.684841Z","signature_b64":"igGVsaZto8jlpJQWHh90XQRVA1XCOGJsL+jAUcyf0TJU7J7Hrid39eAKMpFe20Dj4XTgZn4zp201N9tLhz0QDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f769b69f84806ba960177fbe2ce704704a6565aa732b5a43d5200f8ca23529","last_reissued_at":"2026-07-05T12:00:15.684272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:15.684272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Bolin Shen, Chenxi Zhao, Kaixiang Zhao, Lincan Li, Shirui Pan, Yushun Dong, Yuxiang Sun","submitted_at":"2025-08-27T07:37:52Z","abstract_excerpt":"Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art graph machine learning (GML) models have become increasingly resource-intensive, turning these models and data into invaluable Intellectual Property (IP). To address the resource-intensive nature of model training, graph-based Machine-Learning-as-a-Service (GMLaaS) has emerged as an efficient solution by leveraging third-party cloud services for model development and management. However, deploying such models in GMLaaS a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19641","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/2508.19641/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":"2508.19641","created_at":"2026-07-05T12:00:15.684339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19641v1","created_at":"2026-07-05T12:00:15.684339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19641","created_at":"2026-07-05T12:00:15.684339+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH3WTNU7QSAG","created_at":"2026-07-05T12:00:15.684339+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH3WTNU7QSAGXKLA","created_at":"2026-07-05T12:00:15.684339+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH3WTNU7","created_at":"2026-07-05T12:00:15.684339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19185","citing_title":"AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12827","citing_title":"GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30470","citing_title":"Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12827","citing_title":"GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR","json":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR.json","graph_json":"https://pith.science/api/pith-number/PH3WTNU7QSAGXKLAC5734LHHAR/graph.json","events_json":"https://pith.science/api/pith-number/PH3WTNU7QSAGXKLAC5734LHHAR/events.json","paper":"https://pith.science/paper/PH3WTNU7"},"agent_actions":{"view_html":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR","download_json":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR.json","view_paper":"https://pith.science/paper/PH3WTNU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19641&json=true","fetch_graph":"https://pith.science/api/pith-number/PH3WTNU7QSAGXKLAC5734LHHAR/graph.json","fetch_events":"https://pith.science/api/pith-number/PH3WTNU7QSAGXKLAC5734LHHAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR/action/storage_attestation","attest_author":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR/action/author_attestation","sign_citation":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR/action/citation_signature","submit_replication":"https://pith.science/pith/PH3WTNU7QSAGXKLAC5734LHHAR/action/replication_record"}},"created_at":"2026-07-05T12:00:15.684339+00:00","updated_at":"2026-07-05T12:00:15.684339+00:00"}