{"id":"W4289313429","doi":"10.1186/s42400-022-00119-8","title":"On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities","year":2022,"lang":"en","type":"article","venue":"Cybersecurity","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Huawei Technologies (Canada)","funders":"Huawei Technologies","keywords":"Computer science; Malware; Android (operating system); Software deployment; Malware analysis; Data science; Process (computing); Best practice; Machine learning; Artificial intelligence; Computer security; Software engineering","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":[0.001116358,0.0001509192,0.000215998,0.0001794387,0.0004073116,0.00003621483,0.0003133979,0.00004379733,0.000007699623],"category_scores_gemma":[0.001131666,0.0001623606,0.00004366696,0.0001741972,0.00005425179,0.0004718952,0.0003514847,0.0003281804,1.745833e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005832037,"about_ca_system_score_gemma":0.00005548605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001727915,"about_ca_topic_score_gemma":0.0002906636,"domain_scores_codex":[0.9986351,0.000276456,0.0002415826,0.0004070237,0.0002464867,0.0001934012],"domain_scores_gemma":[0.9983343,0.0006021691,0.0005292894,0.0002549545,0.0002180588,0.00006118202],"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":[0.0009643088,0.0005319109,0.0006835035,0.0008947567,0.0001120937,0.00004973153,0.008474859,0.0008184671,0.004033103,0.07524205,0.0004113913,0.9077838],"study_design_scores_gemma":[0.006859074,0.01923134,0.02264169,0.0004215056,0.0001502226,0.002211347,0.009875598,0.3959326,0.1880929,0.1471272,0.2030943,0.004362149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3512689,0.01268661,0.6285695,0.002628861,0.000857454,0.001645992,0.0001824796,0.001643393,0.0005167862],"genre_scores_gemma":[0.9893025,0.0007517315,0.009538168,0.0001072846,0.00002608571,0.0001878611,0.000008810286,0.0000165758,0.00006097614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9034217,"threshold_uncertainty_score":0.6620873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0929005616227369,"score_gpt":0.3118799947807046,"score_spread":0.2189794331579677,"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."}}