{"id":"W4283071535","doi":"10.36227/techrxiv.20085902.v1","title":"Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Adversarial system; Computer science; Robustness (evolution); Computer security; Cover (algebra); Field (mathematics); Artificial intelligence; Deep learning; Data science; Machine learning; Engineering","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":[0.003311033,0.001907949,0.002081741,0.00179933,0.0007045066,0.002278063,0.002105959,0.003149259,0.002547051],"category_scores_gemma":[0.009736481,0.0008867456,0.001759597,0.001434221,0.002864906,0.004388756,0.003523745,0.004347271,0.001094137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009901484,"about_ca_system_score_gemma":0.0007715689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007711811,"about_ca_topic_score_gemma":0.0005414098,"domain_scores_codex":[0.997538,0.000645668,0.000205307,0.0004255063,0.00097723,0.000208375],"domain_scores_gemma":[0.9930391,0.00506486,0.0004259912,0.000919884,0.000400732,0.0001494779],"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":[0.0002598974,0.0002711091,0.002811363,0.002220536,0.0004363343,0.0003319763,0.0003646646,0.1896592,0.00657699,0.1701449,0.01769637,0.6092267],"study_design_scores_gemma":[0.0000604304,0.0006519554,0.00245463,0.001079759,0.000224665,0.001741511,0.0002198448,0.7199239,0.008910545,0.1965211,0.06808212,0.0001295889],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01265711,0.104556,0.8567319,0.00273339,0.0007043785,0.0002311142,0.0001268152,0.0008761377,0.02138321],"genre_scores_gemma":[0.637907,0.136917,0.2027392,0.002830849,0.002685175,0.0005384734,0.0005998129,0.0005485982,0.0152338],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003311033,"threshold_uncertainty_score":0.01751065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0240394866347675,"score_gpt":0.3164262645323233,"score_spread":0.2923867778975558,"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."}}