{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2LJVAX2YM7KYYX6PLIILRPVVEO","short_pith_number":"pith:2LJVAX2Y","schema_version":"1.0","canonical_sha256":"d2d3505f5867d58c5fcf5a10b8beb5239df7b7018c31c9892df493978866ef8f","source":{"kind":"arxiv","id":"2303.14836","version":1},"attestation_state":"computed","paper":{"title":"Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haoyu He, H. Howie Huang, Yuede Ji","submitted_at":"2023-03-26T22:20:17Z","abstract_excerpt":"Graph neural networks (GNNs) have been utilized to create multi-layer graph models for a number of cybersecurity applications from fraud detection to software vulnerability analysis. Unfortunately, like traditional neural networks, GNNs also suffer from a lack of transparency, that is, it is challenging to interpret the model predictions. Prior works focused on specific factor explanations for a GNN model. In this work, we have designed and implemented Illuminati, a comprehensive and accurate explanation framework for cybersecurity applications using GNN models. Given a graph and a pre-trained"},"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":"2303.14836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-26T22:20:17Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"0ac3c480c9cb24ca22a71aa6c0dc5e47294b68869f7c809f06995de22365fb23","abstract_canon_sha256":"af29f5076a2ec444451126e59a319a0659e77fce99184b8905e2ca605a1870d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:46.721223Z","signature_b64":"ttkI/0tISQDOiJyzmiZh7dDWEKUC4c86QaVP9JSxIwcd0zI1T6Lu6NIettjCUhHSRqPvKCuSOC1L2MeIPjl/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d3505f5867d58c5fcf5a10b8beb5239df7b7018c31c9892df493978866ef8f","last_reissued_at":"2026-07-05T05:54:46.720666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:46.720666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haoyu He, H. Howie Huang, Yuede Ji","submitted_at":"2023-03-26T22:20:17Z","abstract_excerpt":"Graph neural networks (GNNs) have been utilized to create multi-layer graph models for a number of cybersecurity applications from fraud detection to software vulnerability analysis. Unfortunately, like traditional neural networks, GNNs also suffer from a lack of transparency, that is, it is challenging to interpret the model predictions. Prior works focused on specific factor explanations for a GNN model. In this work, we have designed and implemented Illuminati, a comprehensive and accurate explanation framework for cybersecurity applications using GNN models. Given a graph and a pre-trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14836","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/2303.14836/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":"2303.14836","created_at":"2026-07-05T05:54:46.720752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14836v1","created_at":"2026-07-05T05:54:46.720752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14836","created_at":"2026-07-05T05:54:46.720752+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LJVAX2YM7KY","created_at":"2026-07-05T05:54:46.720752+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LJVAX2YM7KYYX6P","created_at":"2026-07-05T05:54:46.720752+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LJVAX2Y","created_at":"2026-07-05T05:54:46.720752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18933","citing_title":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO","json":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO.json","graph_json":"https://pith.science/api/pith-number/2LJVAX2YM7KYYX6PLIILRPVVEO/graph.json","events_json":"https://pith.science/api/pith-number/2LJVAX2YM7KYYX6PLIILRPVVEO/events.json","paper":"https://pith.science/paper/2LJVAX2Y"},"agent_actions":{"view_html":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO","download_json":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO.json","view_paper":"https://pith.science/paper/2LJVAX2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14836&json=true","fetch_graph":"https://pith.science/api/pith-number/2LJVAX2YM7KYYX6PLIILRPVVEO/graph.json","fetch_events":"https://pith.science/api/pith-number/2LJVAX2YM7KYYX6PLIILRPVVEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO/action/storage_attestation","attest_author":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO/action/author_attestation","sign_citation":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO/action/citation_signature","submit_replication":"https://pith.science/pith/2LJVAX2YM7KYYX6PLIILRPVVEO/action/replication_record"}},"created_at":"2026-07-05T05:54:46.720752+00:00","updated_at":"2026-07-05T05:54:46.720752+00:00"}