{"id":"W3136737068","doi":"10.1109/iros51168.2021.9636638","title":"Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Point cloud; Computer science; Artificial intelligence; Computer vision; Adversarial system; Object detection; Benchmark (surveying); RGB color model; Lidar; Key (lock); Domain (mathematical analysis); Point (geometry); Image (mathematics); Object (grammar); Vulnerability (computing); Pattern recognition (psychology); Computer security; Remote sensing; Mathematics; Geography","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":[0.001472504,0.001163167,0.000796169,0.0005060937,0.0004867335,0.0006370574,0.001061006,0.001262738,0.001450348],"category_scores_gemma":[0.005997682,0.0004592322,0.001038772,0.0003190022,0.001703791,0.001530554,0.002747903,0.002035937,0.0003052756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245468,"about_ca_system_score_gemma":0.0005863718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004045431,"about_ca_topic_score_gemma":0.003132592,"domain_scores_codex":[0.9985474,0.0004739789,0.00004320504,0.0002725913,0.0004591954,0.0002035182],"domain_scores_gemma":[0.9972864,0.001779982,0.0002692241,0.0003933161,0.0001712285,0.00009981559],"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":[0.0001264109,0.00002367974,0.0007645617,0.00002443571,0.00005074536,0.00009448684,0.00004107553,0.9729875,0.002866118,0.009589991,0.000880636,0.01255034],"study_design_scores_gemma":[0.000002489095,0.00002218274,0.0001151206,0.000004351418,0.000004054888,0.00002781959,0.000004840798,0.9952715,0.001196413,0.003153783,0.0001923347,0.000005164997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.191846,0.000782249,0.7971965,0.001069512,0.000157088,0.0000947431,0.0002413881,0.001322279,0.007290267],"genre_scores_gemma":[0.9751557,0.0001662707,0.02253353,0.000177252,0.00002760933,0.00003000453,0.0001283043,0.0000588345,0.001722492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004045431,"threshold_uncertainty_score":0.009036541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06681095259077346,"score_gpt":0.3141953886851946,"score_spread":0.2473844360944212,"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."}}