{"id":"W2170770919","doi":"10.1109/cmpsac.2004.1342667","title":"N-gram-based detection of new malicious code","year":2004,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Code (set theory); Signature (topology); Computer virus; Software; Malware; Data mining; Artificial intelligence; Programming language; Computer security","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":[0.0007903779,0.0007409422,0.0006025247,0.00309685,0.0005946964,0.0005242432,0.0005681038,0.0007991585,0.0009834934],"category_scores_gemma":[0.00530362,0.0001153199,0.0003742852,0.001183059,0.0003147877,0.0009447788,0.000669959,0.0005630562,0.001253864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003562329,"about_ca_system_score_gemma":0.0005809945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003568069,"about_ca_topic_score_gemma":0.009542163,"domain_scores_codex":[0.9986603,0.0002582237,0.0001290504,0.0002606887,0.0005244445,0.0001672951],"domain_scores_gemma":[0.9959438,0.001533422,0.0005265342,0.000444021,0.001225943,0.0003262037],"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":[0.001594139,0.0007770638,0.1077979,0.0004659638,0.000159736,0.00125631,0.000592344,0.02022168,0.2060589,0.001186234,0.01270902,0.6471807],"study_design_scores_gemma":[0.00002171022,0.0003156546,0.05985561,0.00003350445,0.00004701627,0.001254218,0.0001834035,0.8244221,0.107278,0.001791702,0.004721113,0.00007604991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8939402,0.0005851144,0.09068161,0.0003601181,0.0001692218,0.0001992765,0.003257146,0.006731578,0.004075688],"genre_scores_gemma":[0.9198371,0.0001095977,0.07438412,0.0000569337,0.0000486381,0.00006781598,0.003275309,0.00009787403,0.002122597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003568069,"threshold_uncertainty_score":0.007094622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03563911430917237,"score_gpt":0.2790708994228318,"score_spread":0.2434317851136594,"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."}}