{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:35F3U7JHIRXZAJE4T27EIPOJD5","short_pith_number":"pith:35F3U7JH","schema_version":"1.0","canonical_sha256":"df4bba7d27446f90249c9ebe443dc91f64e4baba2f36346d3598827f7933a63b","source":{"kind":"arxiv","id":"2110.11024","version":5},"attestation_state":"computed","paper":{"title":"Watermarking Graph Neural Networks based on Backdoor Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jing Xu, Oguzhan Ersoy, Stefanos Koffas, Stjepan Picek","submitted_at":"2021-10-21T09:59:59Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and human expertise in fine-tuning the model. Moreover, with the development of adversarial attacks, e.g., model stealing attacks, GNNs raise challenges to model authentication. To avoid copyright infringement on GNNs, verifying the ownership of the GNN models is necessary.\n  This paper presents a watermarking framework for GNNs for both graph and node classificatio"},"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":"2110.11024","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T09:59:59Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"97cfac5fdcfe21e2006ddc12d693d85773e66d9037fa6e7575e1c1177e742316","abstract_canon_sha256":"ed2fca62da7de9b588d8e8563b4a50407c3d95238dbd2eb0d72aeaf71ac23ff9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:35.963071Z","signature_b64":"aEl+ACm+XlnBrtpUCIDHWs1BTWHG6IYpMMaPKjfDhH7pgFriQHrlFr/TTgcis4gWDcj8GPOT0EcEE2NW1dGCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4bba7d27446f90249c9ebe443dc91f64e4baba2f36346d3598827f7933a63b","last_reissued_at":"2026-07-05T05:15:35.962664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:35.962664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watermarking Graph Neural Networks based on Backdoor Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jing Xu, Oguzhan Ersoy, Stefanos Koffas, Stjepan Picek","submitted_at":"2021-10-21T09:59:59Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and human expertise in fine-tuning the model. Moreover, with the development of adversarial attacks, e.g., model stealing attacks, GNNs raise challenges to model authentication. To avoid copyright infringement on GNNs, verifying the ownership of the GNN models is necessary.\n  This paper presents a watermarking framework for GNNs for both graph and node classificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11024","kind":"arxiv","version":5},"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/2110.11024/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":"2110.11024","created_at":"2026-07-05T05:15:35.962726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11024v5","created_at":"2026-07-05T05:15:35.962726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11024","created_at":"2026-07-05T05:15:35.962726+00:00"},{"alias_kind":"pith_short_12","alias_value":"35F3U7JHIRXZ","created_at":"2026-07-05T05:15:35.962726+00:00"},{"alias_kind":"pith_short_16","alias_value":"35F3U7JHIRXZAJE4","created_at":"2026-07-05T05:15:35.962726+00:00"},{"alias_kind":"pith_short_8","alias_value":"35F3U7JH","created_at":"2026-07-05T05:15:35.962726+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/35F3U7JHIRXZAJE4T27EIPOJD5","json":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5.json","graph_json":"https://pith.science/api/pith-number/35F3U7JHIRXZAJE4T27EIPOJD5/graph.json","events_json":"https://pith.science/api/pith-number/35F3U7JHIRXZAJE4T27EIPOJD5/events.json","paper":"https://pith.science/paper/35F3U7JH"},"agent_actions":{"view_html":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5","download_json":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5.json","view_paper":"https://pith.science/paper/35F3U7JH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11024&json=true","fetch_graph":"https://pith.science/api/pith-number/35F3U7JHIRXZAJE4T27EIPOJD5/graph.json","fetch_events":"https://pith.science/api/pith-number/35F3U7JHIRXZAJE4T27EIPOJD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5/action/storage_attestation","attest_author":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5/action/author_attestation","sign_citation":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5/action/citation_signature","submit_replication":"https://pith.science/pith/35F3U7JHIRXZAJE4T27EIPOJD5/action/replication_record"}},"created_at":"2026-07-05T05:15:35.962726+00:00","updated_at":"2026-07-05T05:15:35.962726+00:00"}