{"id":"W4364305273","doi":"10.1109/aipr57179.2022.10092213","title":"Achieving Adversarial Robustness in Deep Learning-Based Overhead Imaging","year":2022,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Robustness (evolution); Computer science; Adversarial system; Artificial intelligence; Machine learning; Overhead (engineering); Deep learning; Object detection; Pipeline (software); Adversarial machine learning; Pattern recognition (psychology)","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":[0.002249522,0.0009861995,0.0007622907,0.0005303096,0.0003383179,0.0007626176,0.001306117,0.0009764647,0.001001302],"category_scores_gemma":[0.005719095,0.0004247516,0.0005795974,0.0003214035,0.001905432,0.001958112,0.002104967,0.002259206,0.0003079755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001046278,"about_ca_system_score_gemma":0.0007800991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002009588,"about_ca_topic_score_gemma":0.001850318,"domain_scores_codex":[0.9992158,0.0002459469,0.00002764595,0.0001273485,0.0002336939,0.000149521],"domain_scores_gemma":[0.9975508,0.001545087,0.0002781095,0.0003425746,0.0001941591,0.0000892555],"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":[0.000110619,0.00005129171,0.0006949706,0.00003760273,0.00003440434,0.00005743446,0.00004889899,0.9503314,0.005224338,0.009809409,0.0008969672,0.03270261],"study_design_scores_gemma":[0.000002333607,0.0000206371,0.00008034285,0.000005275013,0.000003096398,0.0000137594,0.000004131601,0.9944132,0.001706208,0.003584735,0.0001629158,0.000003348171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0986791,0.0007357628,0.8947192,0.0005974275,0.00007434718,0.00004155979,0.00007536718,0.001394373,0.0036829],"genre_scores_gemma":[0.9516272,0.0002416181,0.04575749,0.0002720168,0.00004145781,0.00003292695,0.0001114372,0.00009278714,0.00182318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002249522,"threshold_uncertainty_score":0.01189679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006728922991036009,"score_gpt":0.2338659007135228,"score_spread":0.2271369777224868,"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."}}