{"id":"W3003526064","doi":"10.1007/978-3-030-45371-8_6","title":"Interpreting Machine Learning Malware Detectors Which Leverage N-gram Analysis","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Interpretability; Malware; Machine learning; Computer science; False positive paradox; Artificial intelligence; Leverage (statistics); False positives and false negatives; Domain (mathematical analysis); Computer security; Data mining","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":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.002534533,0.0009602856,0.001294485,0.00208269,0.0007328375,0.001981112,0.008629468,0.0005555971,0.0000328553],"category_scores_gemma":[0.003391949,0.0009478444,0.0004593208,0.0117601,0.00039763,0.0008293251,0.0119172,0.006226146,0.00002442211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006603023,"about_ca_system_score_gemma":0.0007275797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005011303,"about_ca_topic_score_gemma":0.0005686799,"domain_scores_codex":[0.9915954,0.0007999841,0.001005993,0.003623163,0.00166445,0.001310967],"domain_scores_gemma":[0.9949665,0.001299679,0.000793474,0.002111872,0.0004346021,0.0003938842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008882225,0.00002449517,0.01726726,0.00006435129,0.00009811972,0.00009433024,0.003961873,0.8413532,0.0002023829,0.0001055972,7.69018e-7,0.1368187],"study_design_scores_gemma":[0.0002321263,0.0001113468,0.003704641,0.0002713397,0.00008791674,0.00001896975,0.000002456499,0.9859307,0.001113013,0.007556766,0.00002293615,0.0009477598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01798124,0.0003195436,0.9759774,0.001832845,0.00249665,0.00043342,0.000005590948,0.0008988135,0.00005446381],"genre_scores_gemma":[0.6155624,0.0000115196,0.3835244,0.0005691409,0.0002670257,0.00001636873,0.00001424618,0.00003364544,0.000001314467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5975811,"threshold_uncertainty_score":0.9992972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01488328139086341,"score_gpt":0.2716206282145179,"score_spread":0.2567373468236545,"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."}}