{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001460508,0.001296375,0.0007812738,0.001611635,0.0005367901,0.001970442,0.0007549069,0.001981474,0.002223046],"category_scores_gemma":[0.009230287,0.0004430915,0.0006751341,0.0005738991,0.0008073947,0.002362266,0.001381974,0.00135403,0.001318024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004829814,"about_ca_system_score_gemma":0.0006262634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009358645,"about_ca_topic_score_gemma":0.001319932,"domain_scores_codex":[0.9992404,0.0002043232,0.00004484427,0.0001602695,0.0002516021,0.00009863383],"domain_scores_gemma":[0.996875,0.001520048,0.0003845812,0.0005299882,0.0005569589,0.0001333435],"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":[0.001852176,0.0004611135,0.01864222,0.0003398761,0.0002192205,0.002919618,0.0004306762,0.1814898,0.3546982,0.0443182,0.01173267,0.3828963],"study_design_scores_gemma":[0.00001431871,0.00009472683,0.001846153,0.00002085396,0.00003823337,0.0003313561,0.00007192026,0.9170504,0.04222952,0.03684947,0.001429426,0.00002349047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1839869,0.0004891271,0.8019543,0.0009449631,0.0003889922,0.0001242824,0.000398882,0.005232251,0.00648041],"genre_scores_gemma":[0.8728167,0.0001752463,0.1229129,0.0002240793,0.0001722068,0.00004129555,0.0004202344,0.0004008746,0.002836438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002223046,"threshold_uncertainty_score":0.007723987,"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."}}