{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q4QTDZ6GSOK3LYARZWAKJC32XB","short_pith_number":"pith:Q4QTDZ6G","schema_version":"1.0","canonical_sha256":"872131e7c69395b5e011cd80a48b7ab85d0e43370934a88f03353bdd57feb530","source":{"kind":"arxiv","id":"2506.21106","version":1},"attestation_state":"computed","paper":{"title":"PhishKey: A Novel Centroid-Based Approach for Enhanced Phishing Detection Using Adaptive HTML Component Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Eduardo Fidalgo, Enrique Alegre, Felipe Casta\\~no, Francesco Zola, Raul Orduna, Rocio Alaiz-Rodr\\'iguez","submitted_at":"2025-06-26T09:04:55Z","abstract_excerpt":"Phishing attacks pose a significant cybersecurity threat, evolving rapidly to bypass detection mechanisms and exploit human vulnerabilities. This paper introduces PhishKey to address the challenges of adaptability, robustness, and efficiency. PhishKey is a novel phishing detection method using automatic feature extraction from hybrid sources. PhishKey combines character-level processing with Convolutional Neural Networks (CNN) for URL classification, and a Centroid-Based Key Component Phishing Extractor (CAPE) for HTML content at the word level. CAPE reduces noise and ensures complete sample p"},"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":"2506.21106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-26T09:04:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c4378f08f282a69a40dd3e8d57ae66f9c1c1142edadfcd4ef54b99d7cfa4253","abstract_canon_sha256":"5aa6e26540bc2949523e62e3200285e0893cff4c51c3367c8259d248c0d7a4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:40.201989Z","signature_b64":"I05YSWyYGSevGD0fuPetw4yC3ZzONrRqkCibZSyA5cmWGD+SJclu5jw8G9grrkqy2wsyPZCDjO3vZA10iPZcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872131e7c69395b5e011cd80a48b7ab85d0e43370934a88f03353bdd57feb530","last_reissued_at":"2026-07-05T11:27:40.201525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:40.201525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhishKey: A Novel Centroid-Based Approach for Enhanced Phishing Detection Using Adaptive HTML Component Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Eduardo Fidalgo, Enrique Alegre, Felipe Casta\\~no, Francesco Zola, Raul Orduna, Rocio Alaiz-Rodr\\'iguez","submitted_at":"2025-06-26T09:04:55Z","abstract_excerpt":"Phishing attacks pose a significant cybersecurity threat, evolving rapidly to bypass detection mechanisms and exploit human vulnerabilities. This paper introduces PhishKey to address the challenges of adaptability, robustness, and efficiency. PhishKey is a novel phishing detection method using automatic feature extraction from hybrid sources. PhishKey combines character-level processing with Convolutional Neural Networks (CNN) for URL classification, and a Centroid-Based Key Component Phishing Extractor (CAPE) for HTML content at the word level. CAPE reduces noise and ensures complete sample p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21106","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/2506.21106/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":"2506.21106","created_at":"2026-07-05T11:27:40.201582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21106v1","created_at":"2026-07-05T11:27:40.201582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21106","created_at":"2026-07-05T11:27:40.201582+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4QTDZ6GSOK3","created_at":"2026-07-05T11:27:40.201582+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4QTDZ6GSOK3LYAR","created_at":"2026-07-05T11:27:40.201582+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4QTDZ6G","created_at":"2026-07-05T11:27:40.201582+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/Q4QTDZ6GSOK3LYARZWAKJC32XB","json":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB.json","graph_json":"https://pith.science/api/pith-number/Q4QTDZ6GSOK3LYARZWAKJC32XB/graph.json","events_json":"https://pith.science/api/pith-number/Q4QTDZ6GSOK3LYARZWAKJC32XB/events.json","paper":"https://pith.science/paper/Q4QTDZ6G"},"agent_actions":{"view_html":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB","download_json":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB.json","view_paper":"https://pith.science/paper/Q4QTDZ6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21106&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4QTDZ6GSOK3LYARZWAKJC32XB/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4QTDZ6GSOK3LYARZWAKJC32XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB/action/storage_attestation","attest_author":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB/action/author_attestation","sign_citation":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB/action/citation_signature","submit_replication":"https://pith.science/pith/Q4QTDZ6GSOK3LYARZWAKJC32XB/action/replication_record"}},"created_at":"2026-07-05T11:27:40.201582+00:00","updated_at":"2026-07-05T11:27:40.201582+00:00"}