{"id":"W4387969815","doi":"10.1145/3581783.3612018","title":"Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion","year":2023,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Robustness (evolution); Computer science; Adversarial system; Distortion (music); Noise reduction; Algorithm; Prior probability; Noise (video); Mathematical optimization; Artificial intelligence; Computer vision; Mathematics; Image (mathematics); Telecommunications","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007103924,0.000310227,0.0003083487,0.000324446,0.0004948549,0.0001534174,0.00127596,0.000155369,0.0001091109],"category_scores_gemma":[0.0002482507,0.0002833094,0.0001579903,0.001346603,0.00007193208,0.0007889879,0.001804916,0.0004844208,0.0008665815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001754346,"about_ca_system_score_gemma":0.0000889568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001363924,"about_ca_topic_score_gemma":0.00002116992,"domain_scores_codex":[0.9972577,0.0002161943,0.000385614,0.0007765099,0.0006552355,0.0007087187],"domain_scores_gemma":[0.9984376,0.0003811918,0.0001680915,0.0007380587,0.00007863303,0.0001964322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000250081,0.0002496788,0.004623883,0.00005365827,0.0002154537,0.0008564994,0.007355391,0.3076016,0.01458046,0.2409523,0.01172682,0.4115342],"study_design_scores_gemma":[0.0009154959,0.00009683972,0.002302199,0.00003247672,0.00001067164,0.00001108348,0.0002470189,0.9901507,0.0003047304,0.002988353,0.002520513,0.0004198494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02348503,0.0000116636,0.9522143,0.0007021378,0.002477545,0.0002429857,0.000002010566,0.001725428,0.01913887],"genre_scores_gemma":[0.9000781,0.00001495004,0.09767867,0.0004581779,0.0005369895,0.00001693529,0.00001801125,0.00003918511,0.001158992],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8765931,"threshold_uncertainty_score":0.9999619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01734292886604292,"score_gpt":0.2515388911011982,"score_spread":0.2341959622351553,"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."}}