{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6NLKMXOYVL36ZY4NV6MDG4GDQD","short_pith_number":"pith:6NLKMXOY","schema_version":"1.0","canonical_sha256":"f356a65dd8aaf7ece38daf983370c380e819bf8a629d40be6ddbd8357adf8192","source":{"kind":"arxiv","id":"2606.25589","version":1},"attestation_state":"computed","paper":{"title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Johann Knechtel, Ozgur Sinanoglu, Rupesh Raj Karn","submitted_at":"2026-06-24T08:59:28Z","abstract_excerpt":"As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT, trained on standard netlist benchmarks (ISCAS'85, EPFL, and TrustHub), for their fundamental vulnerability to GLAs. We find that GLAs can expose sensitive infor"},"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":"2606.25589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:59:28Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"443d7109507dcfc889f0fc1e7d5421207ac0d89505009aa41af367f853393922","abstract_canon_sha256":"9890b7e6d4eb7dd05c20be8abde5f278c7d3b6e758e9c01dc1741581fba58c39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:09.762404Z","signature_b64":"HasIW7zx/HsDXOL16/iO204ZKVuJw0vbFiQkQqPxeIHQit6OkfbLqpOUHI2I1Ww07C+nJl17IP8wpDfBPsMfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f356a65dd8aaf7ece38daf983370c380e819bf8a629d40be6ddbd8357adf8192","last_reissued_at":"2026-06-25T01:18:09.762042Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:09.762042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Johann Knechtel, Ozgur Sinanoglu, Rupesh Raj Karn","submitted_at":"2026-06-24T08:59:28Z","abstract_excerpt":"As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT, trained on standard netlist benchmarks (ISCAS'85, EPFL, and TrustHub), for their fundamental vulnerability to GLAs. We find that GLAs can expose sensitive infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25589","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/2606.25589/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":"2606.25589","created_at":"2026-06-25T01:18:09.762106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25589v1","created_at":"2026-06-25T01:18:09.762106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25589","created_at":"2026-06-25T01:18:09.762106+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NLKMXOYVL36","created_at":"2026-06-25T01:18:09.762106+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NLKMXOYVL36ZY4N","created_at":"2026-06-25T01:18:09.762106+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NLKMXOY","created_at":"2026-06-25T01:18:09.762106+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/6NLKMXOYVL36ZY4NV6MDG4GDQD","json":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD.json","graph_json":"https://pith.science/api/pith-number/6NLKMXOYVL36ZY4NV6MDG4GDQD/graph.json","events_json":"https://pith.science/api/pith-number/6NLKMXOYVL36ZY4NV6MDG4GDQD/events.json","paper":"https://pith.science/paper/6NLKMXOY"},"agent_actions":{"view_html":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD","download_json":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD.json","view_paper":"https://pith.science/paper/6NLKMXOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25589&json=true","fetch_graph":"https://pith.science/api/pith-number/6NLKMXOYVL36ZY4NV6MDG4GDQD/graph.json","fetch_events":"https://pith.science/api/pith-number/6NLKMXOYVL36ZY4NV6MDG4GDQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD/action/storage_attestation","attest_author":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD/action/author_attestation","sign_citation":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD/action/citation_signature","submit_replication":"https://pith.science/pith/6NLKMXOYVL36ZY4NV6MDG4GDQD/action/replication_record"}},"created_at":"2026-06-25T01:18:09.762106+00:00","updated_at":"2026-06-25T01:18:09.762106+00:00"}