{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001541375,0.00005213299,0.00006771457,0.00005308651,0.00004251918,0.00002276137,0.0002241401,0.00004410304,0.00001942312],"category_scores_gemma":[0.00002557983,0.00004639497,0.00004018671,0.0002790417,0.00001333351,0.000102695,0.00002852289,0.0000587536,0.00005255271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309627,"about_ca_system_score_gemma":0.0001101884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002256456,"about_ca_topic_score_gemma":0.00008341792,"domain_scores_codex":[0.9994814,0.00001884677,0.0001267822,0.000131836,0.000125593,0.0001155512],"domain_scores_gemma":[0.9996167,0.00001860502,0.00004752533,0.0002088605,0.00004006846,0.00006822806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003967142,0.0001613697,0.001183379,0.00004165634,0.00002110171,0.00001299625,0.00109182,0.01663573,0.1257725,0.6714969,0.0002633476,0.1832795],"study_design_scores_gemma":[0.0005689012,0.0001038576,0.001067538,0.00001037473,0.000002677768,0.000005396307,0.00001086112,0.01916517,0.9617191,0.01508415,0.002162652,0.00009934643],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02769797,0.0000251966,0.9698327,0.001287091,0.0001709062,0.00005734242,5.724077e-7,0.000167478,0.0007607087],"genre_scores_gemma":[0.9467121,7.358576e-7,0.05256765,0.0004133739,0.00002062714,0.000001142209,7.595425e-7,0.000002442463,0.0002811704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9190142,"threshold_uncertainty_score":0.1891932,"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."}}