{"id":"W2905619401","doi":"10.15353/jcvis.v4i1.336","title":"Guarding Against Adversarial Attacks using Biologically Inspired Contour Integration","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Adversarial system; Robustness (evolution); Computer science; Artificial intelligence; System integration; Computer vision; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.001359955,0.0008489289,0.0007696985,0.0005897996,0.0005186415,0.00121838,0.001116722,0.001518016,0.001667054],"category_scores_gemma":[0.006295442,0.0004200894,0.0005401472,0.0003033682,0.002092278,0.001776664,0.002645431,0.002084329,0.0003770003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007051589,"about_ca_system_score_gemma":0.0005324896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007730313,"about_ca_topic_score_gemma":0.0006098549,"domain_scores_codex":[0.9993899,0.0001426908,0.00003072159,0.000119128,0.0002345355,0.00008291824],"domain_scores_gemma":[0.996959,0.001546402,0.0005118548,0.0005615477,0.0002731824,0.0001479667],"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":[0.0002034242,0.00008410202,0.001261211,0.00005047424,0.00008254869,0.0002163342,0.0001401621,0.8562254,0.04454314,0.03370107,0.001290887,0.06220135],"study_design_scores_gemma":[0.000006987469,0.00004970843,0.0001271218,0.00000599742,0.000006690879,0.00004744496,0.000008157439,0.9864749,0.004521364,0.00836232,0.0003812108,0.00000812831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08606587,0.0003778255,0.9073999,0.0004801317,0.00008268132,0.00005271849,0.00002390893,0.0007259485,0.004790993],"genre_scores_gemma":[0.9363775,0.0001851945,0.06115862,0.0002305995,0.00003617234,0.00003739111,0.00003854748,0.00008708615,0.001848966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001667054,"threshold_uncertainty_score":0.007192194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01934336740151162,"score_gpt":0.3128733315685395,"score_spread":0.2935299641670279,"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."}}