{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006732325,0.0008984991,0.001025538,0.01261244,0.001207337,0.002556089,0.0005992091,0.001064282,0.002804504],"category_scores_gemma":[0.004067914,0.0004041583,0.0008217577,0.005145563,0.0005630447,0.003415811,0.001291599,0.0006833366,0.004201163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003614377,"about_ca_system_score_gemma":0.0005365029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001507159,"about_ca_topic_score_gemma":0.002697312,"domain_scores_codex":[0.9986304,0.000252431,0.0001877308,0.0002405463,0.0005480934,0.0001407781],"domain_scores_gemma":[0.9971233,0.001215752,0.0003446956,0.0001970006,0.0009826286,0.0001365287],"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":[0.0004098842,0.0007243496,0.04900947,0.0009333576,0.0002373389,0.001758733,0.0007128908,0.00240389,0.1426568,0.00542727,0.01805537,0.7776706],"study_design_scores_gemma":[0.0001388925,0.001080695,0.1387694,0.0006590653,0.001263036,0.01042819,0.003543261,0.6032651,0.1314485,0.04814289,0.06088274,0.0003782377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.62103,0.006908975,0.3264468,0.0009552847,0.0006783978,0.0007088881,0.005378767,0.01146847,0.02642431],"genre_scores_gemma":[0.841626,0.001656444,0.1419808,0.0002654613,0.0004593791,0.0002039103,0.00662372,0.0004539899,0.006730342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01261244,"threshold_uncertainty_score":0.009382069,"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."}}