{"id":"W4400315154","doi":"10.1109/spw63631.2024.00035","title":"Adversarial 3D Virtual Patches using Integrated Gradients","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Optical Imaging Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Computer science; Computer vision; Artificial intelligence; Computer graphics (images)","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":[0.0004793256,0.0008748139,0.0006586909,0.0002740361,0.0002069291,0.0004223824,0.0008463858,0.0006732916,0.001807092],"category_scores_gemma":[0.001599205,0.0004046977,0.0004883938,0.000166163,0.0009139747,0.000937153,0.001630897,0.0008697071,0.0003613995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003711724,"about_ca_system_score_gemma":0.000351614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001400931,"about_ca_topic_score_gemma":0.001468713,"domain_scores_codex":[0.9996587,0.00007069171,0.00001066374,0.00009150682,0.0001023882,0.00006609577],"domain_scores_gemma":[0.9994261,0.0002620856,0.00007345224,0.0001275168,0.00005518007,0.00005557817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004412567,0.00008097865,0.001928843,0.00008304872,0.00007088057,0.0003386168,0.0001111989,0.8101544,0.04134681,0.01177076,0.002598334,0.1310749],"study_design_scores_gemma":[0.00001319498,0.00008804021,0.0002085211,0.000004768835,0.000006857987,0.000106909,0.00001118772,0.9926932,0.004159625,0.002219419,0.0004826085,0.000005695033],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1417324,0.0003868041,0.853619,0.0002924622,0.0001127422,0.00008707514,0.00007827325,0.00140612,0.002285088],"genre_scores_gemma":[0.9279479,0.0001206477,0.06949781,0.0001444252,0.00003389877,0.0000432801,0.00009880355,0.00009728806,0.002015998],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001807092,"threshold_uncertainty_score":0.006045341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01476481976361438,"score_gpt":0.2428353503133563,"score_spread":0.2280705305497419,"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."}}