{"id":"W4401632402","doi":"10.22215/etd/2024-16076","title":"Robust Defenses Against Adversarial Machine Learning in IoT Security","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Adversarial system; Adversarial machine learning; Context (archaeology); Computer science; Artificial intelligence; Internet of Things; Vulnerability (computing); Set (abstract data type); Machine learning; Computer security; Vulnerability assessment; Data science; Geography","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008295851,0.0006912209,0.000717158,0.0008804685,0.0002419601,0.0004945198,0.001647851,0.0006652689,0.0001624438],"category_scores_gemma":[0.0006446508,0.0006846215,0.0002898075,0.001232099,0.00003811863,0.0004045552,0.0005212573,0.003473963,0.00033566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003052712,"about_ca_system_score_gemma":0.0004428834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009474294,"about_ca_topic_score_gemma":0.004255621,"domain_scores_codex":[0.9959694,0.0003593787,0.0007613219,0.001419464,0.0007862981,0.0007041009],"domain_scores_gemma":[0.9983968,0.0003344314,0.0003196482,0.0006785089,0.0001210841,0.0001495433],"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":[0.0002716767,0.0002584065,0.0027155,0.001302583,0.0002966209,0.001567486,0.02383592,0.826012,0.0002701104,0.07475188,0.002455339,0.06626245],"study_design_scores_gemma":[0.000807252,0.0000843206,0.0005292606,0.0005417712,0.00005439714,0.00001308043,0.0008757397,0.9814994,0.0001571033,0.003767807,0.01055391,0.001116002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2055115,0.007883752,0.243824,0.00185897,0.03827495,0.002618117,0.00003445693,0.008230939,0.4917632],"genre_scores_gemma":[0.9211766,0.0002699865,0.03672699,0.0003419141,0.001225416,0.00008209894,0.001312621,0.0002590292,0.03860537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.715665,"threshold_uncertainty_score":0.9995605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443010138446396,"score_gpt":0.2555331890060016,"score_spread":0.2411030876215376,"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."}}