{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00146437,0.001162592,0.00117132,0.0007005128,0.000572051,0.001003882,0.002576542,0.001935494,0.001584703],"category_scores_gemma":[0.004483148,0.0006793169,0.001239456,0.0004441676,0.002024954,0.001895376,0.004719151,0.003020999,0.0007909837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009407771,"about_ca_system_score_gemma":0.0009096738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002992614,"about_ca_topic_score_gemma":0.00275239,"domain_scores_codex":[0.9990132,0.0001785501,0.00004067406,0.0002142056,0.0004447119,0.0001085823],"domain_scores_gemma":[0.9984988,0.0005548106,0.0002025664,0.000448099,0.0001915718,0.0001041948],"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":[0.000170984,0.00004834424,0.001037551,0.00006607144,0.00009113963,0.0001278742,0.0001231165,0.8648841,0.01811047,0.02452453,0.002821481,0.08799441],"study_design_scores_gemma":[0.000007995643,0.00002187842,0.00006671801,0.000004623368,0.000004340437,0.00003453408,0.000006073965,0.9894215,0.002951869,0.006764583,0.0007083282,0.000007549727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01179999,0.0001846446,0.9853962,0.000208679,0.00004874148,0.00003369151,0.00004562915,0.001293291,0.000989205],"genre_scores_gemma":[0.700289,0.0004711137,0.2922546,0.0006713204,0.00009846248,0.000185748,0.0003517971,0.0005814431,0.005096493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002992614,"threshold_uncertainty_score":0.007744431,"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."}}