{"id":"W3189865072","doi":"","title":"Turning Your Strength against You: Detecting and Mitigating Robust and Universal Adversarial Patch Attack.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Adversarial system; Computer science; Image (mathematics); Artificial intelligence; Inpainting; Deep neural networks; Consistency (knowledge bases); Ambiguity; Pixel; Pattern recognition (psychology); Deep learning; Computer security; Machine learning; Computer vision","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":[0.0009450867,0.001205785,0.0007539436,0.0005723971,0.0004599578,0.0006378578,0.001136732,0.001366226,0.0007734144],"category_scores_gemma":[0.004473486,0.0003999557,0.0006746103,0.000217769,0.00130749,0.001986121,0.001625026,0.001906959,0.0003224688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006844837,"about_ca_system_score_gemma":0.0005610511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002436196,"about_ca_topic_score_gemma":0.003015686,"domain_scores_codex":[0.9992412,0.0001378737,0.00003540265,0.0001958596,0.0002583464,0.0001312982],"domain_scores_gemma":[0.9980332,0.0007870598,0.0003225225,0.000465871,0.0002607777,0.0001305475],"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":[0.001024886,0.000322767,0.01148919,0.0003427173,0.0004139202,0.001291248,0.00042635,0.4568684,0.1169523,0.01167871,0.01183739,0.3873521],"study_design_scores_gemma":[0.00001577175,0.0002358913,0.001294155,0.00001927698,0.00004445296,0.000324307,0.00004596533,0.9621503,0.0312106,0.003036604,0.001601461,0.000021205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3114541,0.002758868,0.6732765,0.001086642,0.0004794386,0.0002298293,0.0001747695,0.004436783,0.006103018],"genre_scores_gemma":[0.9367625,0.0003955865,0.05933487,0.0004708892,0.00006891251,0.00004732716,0.0001939468,0.0001151424,0.00261088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002436196,"threshold_uncertainty_score":0.004998207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05495538597630591,"score_gpt":0.2086710820337805,"score_spread":0.1537156960574745,"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."}}