{"id":"W4224284423","doi":"10.1016/j.cose.2022.102718","title":"AdStop: Efficient flow-based mobile adware detection using machine learning","year":2022,"lang":"en","type":"article","venue":"Computers & Security","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Seneca Polytechnic","funders":"","keywords":"Computer science; Android (operating system); Overhead (engineering); Malware; False positive paradox; Software deployment; Mobile device; Artificial intelligence; Generalizability theory; False positive rate; Machine learning; Real-time computing; Embedded system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844587,0.001369963,0.0009514713,0.002846456,0.0003564811,0.0005223184,0.001146915,0.0006644011,0.002123186],"category_scores_gemma":[0.001527315,0.000383932,0.0006155179,0.000759844,0.0002451681,0.001050284,0.0008174368,0.000744622,0.001840932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004523059,"about_ca_system_score_gemma":0.0006015191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003245781,"about_ca_topic_score_gemma":0.003027625,"domain_scores_codex":[0.999488,0.00006685217,0.00003333344,0.0001699123,0.0001765565,0.00006522836],"domain_scores_gemma":[0.9992802,0.0002889516,0.00010489,0.00008581975,0.0001902506,0.00004986163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005194647,0.0007756883,0.01067358,0.0002431315,0.0001651423,0.0003233884,0.00009446804,0.02814978,0.02481565,0.0006756334,0.02034307,0.9132211],"study_design_scores_gemma":[0.00005480462,0.0002434004,0.005669804,0.00002043833,0.00003831281,0.0002855349,0.00003501653,0.9649143,0.02223285,0.001605262,0.004856221,0.00004392484],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2122157,0.00151939,0.6542793,0.0003900973,0.0004189142,0.0009506863,0.003419673,0.1218905,0.004915808],"genre_scores_gemma":[0.6499911,0.000384983,0.3363544,0.0003345358,0.0001948457,0.0004757084,0.005201296,0.0004762277,0.006586892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003245781,"threshold_uncertainty_score":0.007102728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008861128997836054,"score_gpt":0.2375538261973446,"score_spread":0.2286926971995085,"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."}}