{"id":"W4406610975","doi":"10.1109/tse.2025.3531210","title":"Mecha: A Neural-Symbolic Open-Set Homogeneous Decision Fusion Approach for Zero-Day Malware Similarity Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada); Defence Research and Development Canada; Queen's University","funders":"","keywords":"Computer science; Malware; Similarity (geometry); Zero (linguistics); Set (abstract data type); Artificial intelligence; Homogeneous; Data mining; Artificial neural network; Open set; Machine learning; Algorithm; Pattern recognition (psychology); Programming language; Computer security; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0003947506,0.0004118412,0.0003922101,0.0007093152,0.0005689785,0.0002802424,0.001200769,0.0002813434,0.000007432536],"category_scores_gemma":[0.000119931,0.0004489328,0.0002347429,0.001138763,0.00002282617,0.0008445496,0.00004213946,0.0005156309,0.000005280272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003159544,"about_ca_system_score_gemma":0.00006002598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002524659,"about_ca_topic_score_gemma":0.0000135859,"domain_scores_codex":[0.9977933,0.00005280561,0.0004594824,0.0009132021,0.0002978346,0.0004834306],"domain_scores_gemma":[0.9980973,0.0004956087,0.0000949109,0.0009698385,0.0002067523,0.000135606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008518337,0.0001564351,0.000003108341,0.0001099093,0.00004786564,0.000006839332,0.0001037132,0.530019,0.008753506,0.0002948782,0.0001275591,0.460292],"study_design_scores_gemma":[0.0007835022,0.0002323412,0.00006756974,0.0001101396,0.00003913449,0.0000521889,0.000011135,0.639986,0.3539816,0.00127223,0.002922172,0.0005419177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001696576,0.00007571757,0.9923885,0.00003693861,0.001557034,0.001395229,0.00005124417,0.002775535,0.00002315409],"genre_scores_gemma":[0.5379896,0.00002701521,0.4609263,0.000113316,0.00002420024,0.0007513006,0.000004308455,0.00004037987,0.0001236179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.536293,"threshold_uncertainty_score":0.9997963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01517668517324488,"score_gpt":0.2619306586362847,"score_spread":0.2467539734630398,"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."}}