{"id":"W4378376437","doi":"10.1145/3600094","title":"Taxonomy and Recent Advance of Game Theoretical Approaches in Adversarial Machine Learning: A Survey","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Sensor Networks","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Adversarial system; Computer science; Adversary; Adversarial machine learning; Scope (computer science); Artificial intelligence; Set (abstract data type); Game theory; Taxonomy (biology); Machine learning; Game design; Computer security; Data science; Mathematical economics","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":[0.006463388,0.00237039,0.002171491,0.004174352,0.001108702,0.004719668,0.003257419,0.003167245,0.003936508],"category_scores_gemma":[0.01529421,0.001317976,0.001697057,0.005908125,0.003973715,0.008459439,0.002883184,0.006676732,0.00142467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002842533,"about_ca_system_score_gemma":0.002126202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002396213,"about_ca_topic_score_gemma":0.001504564,"domain_scores_codex":[0.9961157,0.001455021,0.00035687,0.0006863227,0.001177105,0.0002090116],"domain_scores_gemma":[0.9817169,0.01528506,0.0004999067,0.0007498435,0.001470211,0.0002779845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007922629,0.000230752,0.001991771,0.004175025,0.0001694258,0.00017492,0.0005105726,0.03763983,0.0006301015,0.6315207,0.01209333,0.3107844],"study_design_scores_gemma":[0.00003372374,0.0003124669,0.001633393,0.002886402,0.0001387184,0.0008247651,0.000592203,0.1356443,0.0009994183,0.6466046,0.2101509,0.0001791544],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004787714,0.4885817,0.4511755,0.00949612,0.001451487,0.0002218313,0.0002196258,0.000228694,0.04383744],"genre_scores_gemma":[0.1448558,0.6883914,0.1486052,0.004139645,0.005667464,0.0005878565,0.0004719982,0.0001943346,0.007086316],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006463388,"threshold_uncertainty_score":0.03418207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06003432928758818,"score_gpt":0.2653364159620433,"score_spread":0.2053020866744552,"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."}}