{"id":"W2906631928","doi":"10.1109/ccst.2018.8585560","title":"Toward Developing a Systematic Approach to Generate Benchmark Android Malware Datasets and Classification","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":343,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Malware; Random forest; Android malware; Android (operating system); Decision tree; Machine learning; Artificial intelligence; Benchmark (surveying); Mobile malware; Data mining; Precision and recall; Software deployment; Computer security; Operating system","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":[0.0003453653,0.0001445916,0.0001872243,0.0001652613,0.000155901,0.0002048727,0.0005104388,0.00005456356,0.00000352241],"category_scores_gemma":[0.00009426534,0.0001225492,0.0000162513,0.0004719877,0.00003897783,0.0005907517,0.000349078,0.00006004935,0.00004517567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000730449,"about_ca_system_score_gemma":0.00003946379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006754675,"about_ca_topic_score_gemma":0.000004822261,"domain_scores_codex":[0.9987134,0.00007189564,0.0002825066,0.0005272579,0.0001930241,0.0002118583],"domain_scores_gemma":[0.9989925,0.0000370783,0.00009403103,0.0006303924,0.0001392359,0.000106769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005153978,0.0002368434,0.0003542965,0.01564061,0.0001472882,0.00002691442,0.006797924,0.00005184478,0.03997302,0.8121133,0.04596645,0.07863998],"study_design_scores_gemma":[0.00127144,0.001223914,0.008262772,0.003385906,0.00007662204,0.001463801,0.001208899,0.5525374,0.3788447,0.03048646,0.01749808,0.003739962],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001185147,0.00004067942,0.9952034,0.0003364714,0.0001013271,0.000634464,0.000008271933,0.0005149105,0.001975365],"genre_scores_gemma":[0.3368942,0.00000751661,0.6622658,0.0005362421,0.00003791596,0.0001476689,0.00001566227,0.000007411044,0.00008752769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7816268,"threshold_uncertainty_score":0.4997412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05446669555926854,"score_gpt":0.2857373318515801,"score_spread":0.2312706362923116,"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."}}