{"id":"W4413992561","doi":"10.1007/978-3-031-94455-0_5","title":"Siamese Neural Network for Robust IoT Device-Type Identification: A Few-Shot Learning Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Identification (biology); Shot (pellet); Computer science; Artificial neural network; Artificial intelligence; Type (biology); One shot; Single shot; Machine learning; Engineering; Physics; Biology; Materials science; Optics; Mechanical engineering","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0004965777,0.0002996195,0.0003852108,0.0002267478,0.00136907,0.0003172146,0.002275418,0.0002034921,3.472842e-7],"category_scores_gemma":[0.0001399598,0.0002662302,0.0002142933,0.0004728033,0.0002674293,0.0003666097,0.0008555817,0.0005179508,2.030207e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008588839,"about_ca_system_score_gemma":0.0001879413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001212338,"about_ca_topic_score_gemma":0.00002553931,"domain_scores_codex":[0.9985428,0.00001603493,0.0006982684,0.0002447627,0.0002202714,0.0002779013],"domain_scores_gemma":[0.9978696,0.000419442,0.0006107485,0.0006884385,0.0003696808,0.00004209204],"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":[0.000002064973,0.000006744014,0.000001382432,0.0002036365,0.00004098655,2.065623e-8,0.0003482089,0.9291844,0.000005448589,0.04240837,0.0001452149,0.02765349],"study_design_scores_gemma":[0.0001267543,0.00005464236,0.000009806167,0.0001398078,0.0000354755,0.000007534842,0.000002748561,0.9473792,0.00007603657,0.001788175,0.05011695,0.0002628903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001973727,0.0004681927,0.9959104,0.0005318175,0.0006991956,0.0009331485,0.00002126717,0.0002330832,0.001183175],"genre_scores_gemma":[0.002885611,0.00007338839,0.9962473,0.0001768874,0.0001855741,0.00008674571,0.00005031139,0.00001780351,0.0002763839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04997174,"threshold_uncertainty_score":0.999979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03649025178603554,"score_gpt":0.2642721096861984,"score_spread":0.2277818579001628,"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."}}