{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJLN76RUDIUPQAWRUAKIA66XYN","short_pith_number":"pith:YJLN76RU","schema_version":"1.0","canonical_sha256":"c256dffa341a28f802d1a014807bd7c358e373ce181a2be1a2021e0672f19cc6","source":{"kind":"arxiv","id":"2410.17533","version":1},"attestation_state":"computed","paper":{"title":"FedGMark: Certifiably Robust Watermarking for Federated Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"2), (2) Department of Computer Science, (3) School of Computing, Binghui Wang (2) ((1) College of Computer Science, Illinois Institute of Technology, Jilin University, Qiang Li (1), Technology, University of Connecticut), Yuan Hong (3), Yuxin Yang (1","submitted_at":"2024-10-23T03:25:55Z","abstract_excerpt":"Federated graph learning (FedGL) is an emerging learning paradigm to collaboratively train graph data from various clients. However, during the development and deployment of FedGL models, they are susceptible to illegal copying and model theft. Backdoor-based watermarking is a well-known method for mitigating these attacks, as it offers ownership verification to the model owner. We take the first step to protect the ownership of FedGL models via backdoor-based watermarking. Existing techniques have challenges in achieving the goal: 1) they either cannot be directly applied or yield unsatisfact"},"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":"2410.17533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-23T03:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"fde105649a3c631673b8e6b3bdacee429dd1b714b2fe2352002f3c59253ffb2e","abstract_canon_sha256":"35870432b6a00f79a6107f1077a3473679b2fe4d8e195d4c3ebd3ded1cd06a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:23.981742Z","signature_b64":"WNCPJVTy1rjUop6r/7hNyebWMAyqUeET4gSyrEwyrxzf7MAvfBpKTbI7F+ME3A7UraGL1IMISrGeJtKIkRsqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c256dffa341a28f802d1a014807bd7c358e373ce181a2be1a2021e0672f19cc6","last_reissued_at":"2026-07-05T09:24:23.981302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:23.981302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedGMark: Certifiably Robust Watermarking for Federated Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"2), (2) Department of Computer Science, (3) School of Computing, Binghui Wang (2) ((1) College of Computer Science, Illinois Institute of Technology, Jilin University, Qiang Li (1), Technology, University of Connecticut), Yuan Hong (3), Yuxin Yang (1","submitted_at":"2024-10-23T03:25:55Z","abstract_excerpt":"Federated graph learning (FedGL) is an emerging learning paradigm to collaboratively train graph data from various clients. However, during the development and deployment of FedGL models, they are susceptible to illegal copying and model theft. Backdoor-based watermarking is a well-known method for mitigating these attacks, as it offers ownership verification to the model owner. We take the first step to protect the ownership of FedGL models via backdoor-based watermarking. Existing techniques have challenges in achieving the goal: 1) they either cannot be directly applied or yield unsatisfact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17533","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/2410.17533/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":"2410.17533","created_at":"2026-07-05T09:24:23.981379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17533v1","created_at":"2026-07-05T09:24:23.981379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17533","created_at":"2026-07-05T09:24:23.981379+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJLN76RUDIUP","created_at":"2026-07-05T09:24:23.981379+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJLN76RUDIUPQAWR","created_at":"2026-07-05T09:24:23.981379+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJLN76RU","created_at":"2026-07-05T09:24:23.981379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16541","citing_title":"A Comprehensive Data-centric Overview of Federated Graph Learning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN","json":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN.json","graph_json":"https://pith.science/api/pith-number/YJLN76RUDIUPQAWRUAKIA66XYN/graph.json","events_json":"https://pith.science/api/pith-number/YJLN76RUDIUPQAWRUAKIA66XYN/events.json","paper":"https://pith.science/paper/YJLN76RU"},"agent_actions":{"view_html":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN","download_json":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN.json","view_paper":"https://pith.science/paper/YJLN76RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17533&json=true","fetch_graph":"https://pith.science/api/pith-number/YJLN76RUDIUPQAWRUAKIA66XYN/graph.json","fetch_events":"https://pith.science/api/pith-number/YJLN76RUDIUPQAWRUAKIA66XYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN/action/storage_attestation","attest_author":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN/action/author_attestation","sign_citation":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN/action/citation_signature","submit_replication":"https://pith.science/pith/YJLN76RUDIUPQAWRUAKIA66XYN/action/replication_record"}},"created_at":"2026-07-05T09:24:23.981379+00:00","updated_at":"2026-07-05T09:24:23.981379+00:00"}