{"id":"W3125378275","doi":"10.1145/3324884.3418926","title":"On benign features in malware detection","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Malware; Computer science; Android malware; Classifier (UML); Detector; Artificial intelligence; Android (operating system); Machine learning; Data mining; Pattern recognition (psychology); 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":[0.00005058139,0.00008859131,0.00008335952,0.00009723302,0.00003816736,0.00004346134,0.0003268156,0.00005428246,0.00002194385],"category_scores_gemma":[0.00008996682,0.0000817909,0.0000299704,0.0004790331,0.000009295884,0.0003066015,0.00009345787,0.0001834849,0.00005156686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004329532,"about_ca_system_score_gemma":0.000009229726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001851026,"about_ca_topic_score_gemma":0.00005383201,"domain_scores_codex":[0.9992712,0.00002859509,0.0001089551,0.0003142378,0.0001396853,0.000137293],"domain_scores_gemma":[0.999619,0.00004480022,0.00002966378,0.0002200763,0.00002443645,0.00006203319],"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":[0.00009020141,0.00007895731,0.0001416442,0.00002698121,0.000007405542,0.00009247867,0.0009464177,0.002186243,0.0358316,0.1396796,0.004111719,0.8168068],"study_design_scores_gemma":[0.0003229716,0.0006767715,0.003007776,0.00001467053,9.302801e-7,0.00001716531,0.0000408026,0.01635093,0.9417207,0.03271203,0.004837292,0.0002979855],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004344663,0.00001275408,0.9881783,0.001814124,0.00008652233,0.0001328349,3.727902e-7,0.001157249,0.00427318],"genre_scores_gemma":[0.9529373,0.000003647523,0.04425502,0.002625502,0.00002901722,0.00002142532,2.467855e-7,0.000006579666,0.0001212791],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9485926,"threshold_uncertainty_score":0.3335336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0100288186304092,"score_gpt":0.2377593318081216,"score_spread":0.2277305131777124,"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."}}