{"id":"W4402264355","doi":"10.1109/sp54263.2024.00243","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Government of Ontario","keywords":"Unintended consequences; Computer science; Machine learning; Human–computer interaction; Risk analysis (engineering); Business; Political science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002755429,0.0001539156,0.0001350714,0.0002097649,0.0002559872,0.0005130885,0.0003307756,0.00004530045,0.0001210241],"category_scores_gemma":[0.0002382143,0.000130385,0.00005767647,0.0003771065,0.0001114527,0.0009114646,0.0004964013,0.0007210301,0.00007702609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003889927,"about_ca_system_score_gemma":0.00003162671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006105098,"about_ca_topic_score_gemma":0.0001203513,"domain_scores_codex":[0.9988917,0.0001002825,0.0001780454,0.0004334518,0.000160983,0.0002355602],"domain_scores_gemma":[0.9992503,0.0003451995,0.00004056618,0.0002326962,0.00003961807,0.00009161637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001098569,0.00003745245,0.03424874,0.0000763308,0.0001597599,0.0002524605,0.00334824,0.03778576,0.0005096187,0.7250235,0.000736507,0.1978106],"study_design_scores_gemma":[0.00009727821,0.00003310629,0.00416716,0.00005402233,0.00001396283,0.00007798672,0.0001335313,0.980616,0.0001172385,0.003921402,0.01059275,0.0001755959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01900193,0.0003654113,0.9659083,0.00133752,0.0007409843,0.00007235117,6.047743e-7,0.001091098,0.01148175],"genre_scores_gemma":[0.9577209,0.00002572561,0.0376238,0.00008080176,0.00008730395,0.000006203059,0.000002949306,0.00001781548,0.004434464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9428302,"threshold_uncertainty_score":0.5316947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02972554940440073,"score_gpt":0.3047028500296028,"score_spread":0.2749773006252021,"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."}}