{"id":"W4386838570","doi":"10.18280/ria.370422","title":"Multi-Modal Deep Learning for Effective Malicious Webpage Detection","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Web page; Computer science; JavaScript; Malware; Deep learning; Feature (linguistics); Artificial intelligence; Machine learning; Information retrieval; Data mining; World Wide Web; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007467413,0.0001672537,0.0001743264,0.0002491953,0.0004991485,0.0001737803,0.0004683159,0.000119557,0.0000133553],"category_scores_gemma":[0.0004104633,0.0001775427,0.0001478995,0.001102788,0.00004110066,0.000330408,0.0001271976,0.0002557252,0.0009400055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008023504,"about_ca_system_score_gemma":0.00001314413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004799585,"about_ca_topic_score_gemma":0.00006912381,"domain_scores_codex":[0.9984776,0.0001091216,0.0002793619,0.0005581549,0.0001459707,0.0004298418],"domain_scores_gemma":[0.9988025,0.0004840879,0.0001098932,0.0003947792,0.0001220176,0.00008673374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003417807,0.00007045078,0.000207985,0.00007621469,0.00002484582,0.00001501172,0.003923021,0.1929947,0.08666511,0.001368131,0.00008947092,0.7145309],"study_design_scores_gemma":[0.00006374931,0.0002483988,0.0004949173,0.00002224933,0.000006586527,0.00001790771,0.00023263,0.8272241,0.1658013,0.001042476,0.00466634,0.000179349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05180968,0.00007963731,0.944998,0.0002147478,0.00129572,0.0005697014,9.823324e-7,0.0007944512,0.0002371208],"genre_scores_gemma":[0.9929332,0.00003217272,0.004980111,0.00005096031,0.0001874973,0.000245052,0.00000526588,0.0000238734,0.001541859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9411235,"threshold_uncertainty_score":0.9998379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03172869535004404,"score_gpt":0.2797017606152627,"score_spread":0.2479730652652186,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}