{"id":"W4364382428","doi":"10.1016/j.eswa.2023.120017","title":"SwiftR: Cross-platform ransomware fingerprinting using hierarchical neural networks on hybrid features","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Ransomware; Computer science; Static analysis; Artificial neural network; Artificial intelligence; Code (set theory); Machine learning; Word (group theory); Data mining; Theoretical computer science; Set (abstract data type); Malware; Computer security; Programming language","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":[0.0006223221,0.001308773,0.0008506245,0.001481833,0.0003316057,0.0006461426,0.001168197,0.0009156513,0.00378125],"category_scores_gemma":[0.001586386,0.0004722276,0.0005350056,0.0008450429,0.0001967604,0.001449479,0.001485949,0.0007967481,0.002268318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002889027,"about_ca_system_score_gemma":0.0005149413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003366589,"about_ca_topic_score_gemma":0.006599559,"domain_scores_codex":[0.9994889,0.00005816793,0.0000264795,0.0001305107,0.00019609,0.00009973835],"domain_scores_gemma":[0.9994629,0.0001413542,0.00006938186,0.0001694003,0.0001196877,0.00003726345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005313717,0.0003229079,0.003840598,0.0001026637,0.0001942577,0.0002755834,0.00005838896,0.03009329,0.03945138,0.001198362,0.01485171,0.9090796],"study_design_scores_gemma":[0.0000270438,0.0001652933,0.002006479,0.00001079276,0.00002890313,0.0002018941,0.0000279124,0.9683558,0.02561544,0.001175092,0.002357138,0.0000282091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1443771,0.0007822384,0.7925684,0.0001919619,0.0003056056,0.0002514999,0.001360939,0.05606697,0.004095309],"genre_scores_gemma":[0.5378196,0.0002188426,0.4474394,0.0001959024,0.00007324795,0.0001528868,0.003206127,0.0007810693,0.010113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00378125,"threshold_uncertainty_score":0.0126496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02229832980699998,"score_gpt":0.3073305714782253,"score_spread":0.2850322416712253,"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."}}