{"id":"W4402563142","doi":"10.14722/sdiotsec.2024.23066","title":"Make your IoT environments robust against adversarial machine learning malware threats: a code-cave approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Malware; Computer science; Adversarial system; Cave; Code (set theory); Internet of Things; Adversarial machine learning; Computer security; Artificial intelligence; Machine learning; 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":[0.002183526,0.0008464463,0.0005594773,0.001237696,0.0006329604,0.001858779,0.001657982,0.001637292,0.001634615],"category_scores_gemma":[0.01321275,0.0004706689,0.0006622346,0.0004243143,0.002149069,0.004394038,0.003705356,0.002240234,0.0008989915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006414063,"about_ca_system_score_gemma":0.00126945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001564404,"about_ca_topic_score_gemma":0.001934722,"domain_scores_codex":[0.9987809,0.0003170636,0.00004539234,0.0002104575,0.0004736956,0.0001725521],"domain_scores_gemma":[0.9947457,0.001851203,0.0007324731,0.001734702,0.0007217942,0.0002140614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003357018,0.0004836954,0.01202235,0.0003239658,0.0001449805,0.000695523,0.000586978,0.5321792,0.0409415,0.05576846,0.008516282,0.3480014],"study_design_scores_gemma":[0.00001202542,0.0001291869,0.001134746,0.00006303585,0.00002251167,0.000292961,0.0001149216,0.9584735,0.01104097,0.02334157,0.005350278,0.00002438585],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1402126,0.0009497547,0.8367649,0.004179061,0.0002234818,0.0003737053,0.000173029,0.005055842,0.01206751],"genre_scores_gemma":[0.8525617,0.0005697465,0.1403397,0.0007691347,0.00009735675,0.0001643363,0.0002978259,0.0004128492,0.004787484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002183526,"threshold_uncertainty_score":0.01154774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02898858246510753,"score_gpt":0.2304920978367645,"score_spread":0.201503515371657,"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."}}