{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005293547,0.0003939049,0.0004569244,0.0002524737,0.0003433995,0.0007477259,0.0007937628,0.000221647,0.0001314962],"category_scores_gemma":[0.0002190167,0.0003782148,0.0001871788,0.0002202439,0.00007232961,0.0005272314,0.000217037,0.0004886203,0.00007505716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002904784,"about_ca_system_score_gemma":0.0002186855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002568896,"about_ca_topic_score_gemma":0.00006372444,"domain_scores_codex":[0.9967801,0.0002431368,0.0006611376,0.001053667,0.0008406613,0.0004213285],"domain_scores_gemma":[0.9978019,0.0003153589,0.0003387214,0.000569634,0.0007840573,0.0001903223],"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":[0.0001684221,0.0001573615,0.00009144186,0.00006379953,0.0002209962,0.00006866613,0.0009982561,0.5626191,0.003205406,0.3926039,0.0003837434,0.03941888],"study_design_scores_gemma":[0.0006474726,0.0002611776,0.00003332134,0.0002847408,0.00002350831,0.00004823159,0.000404242,0.9864475,0.00363398,0.002284526,0.005518277,0.0004129949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005242975,0.0001022477,0.9760103,0.0007861253,0.01005055,0.0004920798,0.00004201394,0.00009199837,0.007181745],"genre_scores_gemma":[0.9887884,0.00018117,0.005433348,0.0002749044,0.001174129,0.0001367295,0.000051615,0.00003552076,0.003924203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9835454,"threshold_uncertainty_score":0.999867,"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."}}