{"id":"W7129047569","doi":"10.1109/iemcon67450.2025.11381086","title":"NLP-based Cyber Threat Data Analysis with MITRE ATT&CK Techniques","year":2025,"lang":"","type":"article","venue":"","topic":"Cybercrime and Law Enforcement Studies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Classifier (UML); Process (computing); Cyber threats; Plan (archaeology); Random forest; Natural language","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":[0.002286314,0.000777216,0.000472062,0.005500644,0.001086947,0.001745565,0.001013505,0.001163877,0.005163473],"category_scores_gemma":[0.008164338,0.0002540287,0.000830963,0.002673229,0.0006765404,0.002716571,0.001630417,0.001798411,0.003778866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156949,"about_ca_system_score_gemma":0.001270053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006838073,"about_ca_topic_score_gemma":0.009722294,"domain_scores_codex":[0.9974985,0.0007713294,0.000282474,0.0007173513,0.0006097678,0.0001205643],"domain_scores_gemma":[0.9954999,0.002155385,0.0005107013,0.0008807489,0.0008836717,0.00006964072],"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":[0.0002459909,0.0004525178,0.01124695,0.0009407785,0.0001454614,0.001359852,0.002733702,0.02413787,0.03599924,0.0126139,0.04016518,0.8699586],"study_design_scores_gemma":[0.00004700719,0.0002134517,0.02700452,0.0002713829,0.0001589068,0.001233116,0.002905556,0.7504869,0.05086726,0.04063531,0.1260036,0.0001729538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07995974,0.001021441,0.8399528,0.002148754,0.0003057774,0.0008787694,0.01426192,0.04101485,0.02045607],"genre_scores_gemma":[0.3555513,0.0003882282,0.612191,0.0004297825,0.0001339081,0.0007979512,0.02197512,0.0007001976,0.007832625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006838073,"threshold_uncertainty_score":0.01727349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04980864084180939,"score_gpt":0.3258318472866225,"score_spread":0.276023206444813,"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."}}