{"id":"W4387896026","doi":"10.54254/2755-2721/19/20231029","title":"Review of Adversarial Attacks in Object Detection","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Adversarial system; Computer science; Object (grammar); Exploit; Object detection; Computer security; Artificial intelligence; Deep learning; Masking (illustration); Adversarial machine learning; Risk analysis (engineering); Data science; Pattern recognition (psychology); Business","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":[],"consensus_categories":[],"category_scores_codex":[0.0002542868,0.00007389756,0.0001306661,0.0001533433,0.0000259913,0.00001142127,0.0001336092,0.00002722296,0.000001857192],"category_scores_gemma":[0.00005028157,0.00008104696,0.00002131799,0.0006311492,0.000009062297,0.00009490014,0.0001085807,0.0001112719,0.00000631344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001869433,"about_ca_system_score_gemma":0.00001972011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006530582,"about_ca_topic_score_gemma":4.961955e-7,"domain_scores_codex":[0.999396,0.00001069312,0.0001783872,0.0001637239,0.0001396109,0.0001116179],"domain_scores_gemma":[0.9996653,0.0001662863,0.00004454692,0.00007965577,0.00002038516,0.00002384366],"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":[0.000002094059,0.000003594012,0.00003164751,0.0004221903,0.000005573525,0.000002040387,0.00009237557,0.9548956,0.0003404719,0.02436007,0.00001366496,0.01983064],"study_design_scores_gemma":[0.0002629011,0.000009597765,0.005413936,0.0003563696,0.000002556246,0.000004091535,0.000006997876,0.99191,0.00008898188,0.001565357,0.0002871924,0.00009202899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008678533,0.0004681344,0.9899969,0.00009944728,0.0001703303,0.0001165269,5.096273e-7,0.0001595062,0.0003101183],"genre_scores_gemma":[0.9804447,0.0001845245,0.0192193,0.00007788997,0.00004355958,0.00001400851,0.000006115208,0.00000687344,0.000003066731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9717661,"threshold_uncertainty_score":0.3304999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00712527573519359,"score_gpt":0.2342225647876421,"score_spread":0.2270972890524486,"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."}}