{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:54BF2EY6GRYPKUIYPZ57DD6WYM","short_pith_number":"pith:54BF2EY6","schema_version":"1.0","canonical_sha256":"ef025d131e3470f551187e7bf18fd6c33886fe574734f1b52917f46a6e1c78f0","source":{"kind":"arxiv","id":"2309.08569","version":2},"attestation_state":"computed","paper":{"title":"Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Karuna Bhaila, Wen Huang, Xintao Wu, Yongkai Wu","submitted_at":"2023-09-15T17:35:51Z","abstract_excerpt":"Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework that can provide node privacy at the user level, while incurring low utility loss. We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training. Specifically, we inves"},"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":"2309.08569","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:35:51Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"2ae6c67a36eeecf59a999ba85ff274968f0f9d9644b43644eafd039e9095d7a1","abstract_canon_sha256":"268e56e54cddd4880b7d172c20d3ce8e9cb1bed2c274bfd020954707bceed195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:26.523724Z","signature_b64":"B1lxMKIHLBTxCpsF4DjevSJqLjt5AtpercI4dpp/oq7J5yRnrGr5x7v8l9QP3uLdmzQNzGZIPeZe5IkbAs/5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef025d131e3470f551187e7bf18fd6c33886fe574734f1b52917f46a6e1c78f0","last_reissued_at":"2026-07-05T08:52:26.523373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:26.523373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Karuna Bhaila, Wen Huang, Xintao Wu, Yongkai Wu","submitted_at":"2023-09-15T17:35:51Z","abstract_excerpt":"Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework that can provide node privacy at the user level, while incurring low utility loss. We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training. Specifically, we inves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08569","kind":"arxiv","version":2},"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/2309.08569/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":"2309.08569","created_at":"2026-07-05T08:52:26.523434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08569v2","created_at":"2026-07-05T08:52:26.523434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08569","created_at":"2026-07-05T08:52:26.523434+00:00"},{"alias_kind":"pith_short_12","alias_value":"54BF2EY6GRYP","created_at":"2026-07-05T08:52:26.523434+00:00"},{"alias_kind":"pith_short_16","alias_value":"54BF2EY6GRYPKUIY","created_at":"2026-07-05T08:52:26.523434+00:00"},{"alias_kind":"pith_short_8","alias_value":"54BF2EY6","created_at":"2026-07-05T08:52:26.523434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02134","citing_title":"ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM","json":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM.json","graph_json":"https://pith.science/api/pith-number/54BF2EY6GRYPKUIYPZ57DD6WYM/graph.json","events_json":"https://pith.science/api/pith-number/54BF2EY6GRYPKUIYPZ57DD6WYM/events.json","paper":"https://pith.science/paper/54BF2EY6"},"agent_actions":{"view_html":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM","download_json":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM.json","view_paper":"https://pith.science/paper/54BF2EY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08569&json=true","fetch_graph":"https://pith.science/api/pith-number/54BF2EY6GRYPKUIYPZ57DD6WYM/graph.json","fetch_events":"https://pith.science/api/pith-number/54BF2EY6GRYPKUIYPZ57DD6WYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM/action/storage_attestation","attest_author":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM/action/author_attestation","sign_citation":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM/action/citation_signature","submit_replication":"https://pith.science/pith/54BF2EY6GRYPKUIYPZ57DD6WYM/action/replication_record"}},"created_at":"2026-07-05T08:52:26.523434+00:00","updated_at":"2026-07-05T08:52:26.523434+00:00"}