{"id":"W4297099963","doi":"10.1109/dsc54232.2022.9888835","title":"Malicious and Benign URL Dataset Generation Using Character-Level LSTM Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Blacklist; Classifier (UML); Artificial intelligence; Machine learning; Character (mathematics); Similarity (geometry); Data mining; Information retrieval; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.0002426231,0.00006701193,0.0000628117,0.0000688885,0.0003712524,0.0001772613,0.0002332832,0.00001939988,0.00003956039],"category_scores_gemma":[0.000003708301,0.00006834944,0.00001281464,0.0001482516,0.000007812431,0.0007131514,0.0002998944,0.000087946,0.000003362604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003991247,"about_ca_system_score_gemma":0.00002313572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003979098,"about_ca_topic_score_gemma":0.00002653863,"domain_scores_codex":[0.9992755,0.00006278093,0.0001037083,0.0002620051,0.0001792402,0.0001167783],"domain_scores_gemma":[0.9996082,0.00001326903,0.00004102268,0.0002810036,0.0000157327,0.00004075738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004222847,0.0003454647,0.0006474704,0.00003582581,0.00009028532,0.00008216396,0.006204523,0.1087833,0.424841,0.2523556,0.06690357,0.1396686],"study_design_scores_gemma":[0.0001110077,0.00004277968,0.0001729201,7.517868e-7,0.000003772448,0.00007600013,0.00001208198,0.992266,0.001782218,0.001716774,0.003712552,0.0001031552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2987698,0.00003981373,0.6999633,0.0003230117,0.0004617571,0.00008139905,0.0001754762,0.00007073938,0.0001146642],"genre_scores_gemma":[0.9758,0.000004648732,0.02264073,0.001036715,0.0001333642,0.00001028382,0.0002403008,0.000005829055,0.0001280919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8834827,"threshold_uncertainty_score":0.2855411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1701835766062939,"score_gpt":0.2668449957888401,"score_spread":0.09666141918254628,"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."}}