{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:USZNPZILURTG6YLSQJDVCGTDCF","short_pith_number":"pith:USZNPZIL","schema_version":"1.0","canonical_sha256":"a4b2d7e50ba4666f61728247511a631174c9fac1431cf89adc95f25888f900f2","source":{"kind":"arxiv","id":"2412.02301","version":1},"attestation_state":"computed","paper":{"title":"Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.AI","authors_text":"Ali Chehab, Fouad Trad","submitted_at":"2024-12-03T09:13:52Z","abstract_excerpt":"With the rise of sophisticated phishing attacks, there is a growing need for effective and economical detection solutions. This paper explores the use of large multimodal agents, specifically Gemini 1.5 Flash and GPT-4o mini, to analyze both URLs and webpage screenshots via APIs, thus avoiding the complexities of training and maintaining AI systems. Our findings indicate that integrating these two data types substantially enhances detection performance over using either type alone. However, API usage incurs costs per query that depend on the number of input and output tokens. To address this, "},"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":"2412.02301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-03T09:13:52Z","cross_cats_sorted":["cs.CL","cs.CR"],"title_canon_sha256":"9b374b36111b4b576e9b4d8bcb46ddb80cb8e1f17ff441ef46384c0a2a0b317b","abstract_canon_sha256":"06966668d76feeb861185026bc2fd2d84f6a1f7621d1cf66ba5bb25e9159b545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:46.055813Z","signature_b64":"sd6/AIKiWvseMeR3BzNZPnAiLR4Ej3We0IOldfOip4F2Da6lagC7ygRgEq1++aUzX9WlJrcFZAkSFHprHbMeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4b2d7e50ba4666f61728247511a631174c9fac1431cf89adc95f25888f900f2","last_reissued_at":"2026-07-05T10:06:46.055390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:46.055390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.AI","authors_text":"Ali Chehab, Fouad Trad","submitted_at":"2024-12-03T09:13:52Z","abstract_excerpt":"With the rise of sophisticated phishing attacks, there is a growing need for effective and economical detection solutions. This paper explores the use of large multimodal agents, specifically Gemini 1.5 Flash and GPT-4o mini, to analyze both URLs and webpage screenshots via APIs, thus avoiding the complexities of training and maintaining AI systems. Our findings indicate that integrating these two data types substantially enhances detection performance over using either type alone. However, API usage incurs costs per query that depend on the number of input and output tokens. To address this, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02301","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/2412.02301/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":"2412.02301","created_at":"2026-07-05T10:06:46.055448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02301v1","created_at":"2026-07-05T10:06:46.055448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02301","created_at":"2026-07-05T10:06:46.055448+00:00"},{"alias_kind":"pith_short_12","alias_value":"USZNPZILURTG","created_at":"2026-07-05T10:06:46.055448+00:00"},{"alias_kind":"pith_short_16","alias_value":"USZNPZILURTG6YLS","created_at":"2026-07-05T10:06:46.055448+00:00"},{"alias_kind":"pith_short_8","alias_value":"USZNPZIL","created_at":"2026-07-05T10:06:46.055448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04759","citing_title":"Enhancing Phishing Email Identification with Large Language Models","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF","json":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF.json","graph_json":"https://pith.science/api/pith-number/USZNPZILURTG6YLSQJDVCGTDCF/graph.json","events_json":"https://pith.science/api/pith-number/USZNPZILURTG6YLSQJDVCGTDCF/events.json","paper":"https://pith.science/paper/USZNPZIL"},"agent_actions":{"view_html":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF","download_json":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF.json","view_paper":"https://pith.science/paper/USZNPZIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/USZNPZILURTG6YLSQJDVCGTDCF/graph.json","fetch_events":"https://pith.science/api/pith-number/USZNPZILURTG6YLSQJDVCGTDCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF/action/storage_attestation","attest_author":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF/action/author_attestation","sign_citation":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF/action/citation_signature","submit_replication":"https://pith.science/pith/USZNPZILURTG6YLSQJDVCGTDCF/action/replication_record"}},"created_at":"2026-07-05T10:06:46.055448+00:00","updated_at":"2026-07-05T10:06:46.055448+00:00"}