{"id":"W3107757457","doi":"10.1007/s40747-020-00233-5","title":"Embedded YARA rules: strengthening YARA rules utilising fuzzy hashing and fuzzy rules for malware analysis","year":2020,"lang":"en","type":"article","venue":"Complex & Intelligent Systems","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Malware; Data mining; Fuzzy logic; Malware analysis; Ransomware; Hash function; Probabilistic logic; Machine learning; Artificial intelligence; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006017209,0.0005836164,0.001036651,0.0005817285,0.0006142703,0.001064359,0.001397213,0.0001911413,0.00002146232],"category_scores_gemma":[0.0003282527,0.0005843515,0.0004372292,0.000941892,0.0001403378,0.0008807225,0.0006077582,0.0003453654,0.00005793162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001764499,"about_ca_system_score_gemma":0.000056245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001117605,"about_ca_topic_score_gemma":0.0000242983,"domain_scores_codex":[0.995879,0.0002371235,0.001211399,0.001352327,0.0005756835,0.0007444668],"domain_scores_gemma":[0.9970388,0.0005801406,0.0006256194,0.0009715691,0.000386103,0.0003977319],"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":[0.0005832642,0.0005983556,0.005999298,0.005426015,0.006210072,0.0002475555,0.05078514,0.04983285,0.03504709,0.3578171,0.01062755,0.4768257],"study_design_scores_gemma":[0.0006412193,0.0005279966,0.0007479897,0.0005594079,0.000461293,0.00008755004,0.005087144,0.9304901,0.01526079,0.01291586,0.03144813,0.0017725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03992392,0.001635684,0.9543201,0.0003225791,0.0004127341,0.001052526,0.0001447975,0.001570416,0.0006172091],"genre_scores_gemma":[0.8364881,0.00007368821,0.1624195,0.0002445796,0.0003357121,0.0001829126,0.0001060634,0.00006259789,0.00008681593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8806573,"threshold_uncertainty_score":0.9999726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07404297900241157,"score_gpt":0.307322885469279,"score_spread":0.2332799064668674,"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."}}