{"id":"W2521519773","doi":"10.1007/978-3-319-46298-1_30","title":"Detecting Malicious URLs Using Lexical Analysis","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":187,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Blacklisting; Obfuscation; Malware; Set (abstract data type); Domain name; Phishing; Honeypot; Categorization; Computer security; Blacklist; World Wide Web; The Internet; Domain (mathematical analysis); Information retrieval; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001380749,0.0004995354,0.0006288149,0.001848655,0.0004382369,0.0007376428,0.002191255,0.000414428,0.00002624906],"category_scores_gemma":[0.0001478986,0.0004134994,0.0003202598,0.001699754,0.0004243566,0.0006950823,0.001054096,0.000713723,0.00004227492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004894648,"about_ca_system_score_gemma":0.0003207183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008194846,"about_ca_topic_score_gemma":0.0002077841,"domain_scores_codex":[0.9959559,0.00006863179,0.0005390402,0.001691521,0.001012597,0.0007323063],"domain_scores_gemma":[0.9971786,0.0006065078,0.0003558802,0.001445235,0.0002124978,0.0002013037],"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":[0.000007661019,0.00001793716,0.0004069814,0.00002093401,0.0001145739,0.000149561,0.0005593413,0.0726551,0.001787851,0.009425852,0.000002967511,0.9148512],"study_design_scores_gemma":[0.0001770963,0.0001094196,0.0002057946,0.0002202394,0.00008991525,0.0001370607,7.21731e-8,0.918476,0.003327478,0.076106,0.0003827665,0.0007681088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008122789,0.0002019963,0.9947646,0.0002897946,0.002011209,0.0001831515,0.000003162536,0.0002442042,0.001489571],"genre_scores_gemma":[0.7105703,0.00001280841,0.2873584,0.0007694427,0.0009913393,0.000003625223,0.000001071637,0.00003702457,0.0002558955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9140831,"threshold_uncertainty_score":0.9998317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0252092243512414,"score_gpt":0.2615634480667581,"score_spread":0.2363542237155167,"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."}}