{"id":"W4387735260","doi":"10.1145/3627817","title":"It Is All about Data: A Survey on the Effects of Data on Adversarial Robustness","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Adversarial system; Robustness (evolution); Computer science; Machine learning; Artificial intelligence; Mistake; Vulnerability (computing); Adversarial machine learning; Computer security; Threat model; Data science","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":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.03218793,0.001166971,0.002938492,0.0004547962,0.0004985046,0.0004720743,0.03918001,0.0005810058,0.00001362575],"category_scores_gemma":[0.03688705,0.0008481488,0.0003606277,0.002495761,0.0002199212,0.0005943745,0.03168865,0.002446449,0.0003005793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001581864,"about_ca_system_score_gemma":0.0007845754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001408804,"about_ca_topic_score_gemma":0.000231761,"domain_scores_codex":[0.9750369,0.01721551,0.001711487,0.003260402,0.001687177,0.001088527],"domain_scores_gemma":[0.9017277,0.0759661,0.002047048,0.01985347,0.0002302877,0.000175372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001061746,0.0001433053,0.0000593267,0.0062491,0.0009211877,0.0001036947,0.0002529714,0.005164638,5.322153e-8,0.0004214096,0.06864921,0.9180245],"study_design_scores_gemma":[0.00137888,0.0004714703,0.002720079,0.04883706,0.0009471067,0.00002698603,0.00001233507,0.3546993,0.000001272455,0.0001263421,0.5880471,0.002732037],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.0000323462,0.3882026,0.5886898,0.00102297,0.01521401,0.003547621,0.001873047,0.001104138,0.000313525],"genre_scores_gemma":[0.0003766212,0.967891,0.01802789,0.001410596,0.002742447,0.0000347457,0.008487097,0.0005612668,0.000468282],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9152924,"threshold_uncertainty_score":0.9998549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2351525607181049,"score_gpt":0.4152004103574418,"score_spread":0.1800478496393369,"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."}}