{"id":"W4399019310","doi":"10.2139/ssrn.4840878","title":"Adversarial Defenses Via Vector Quantization","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Adversarial system; Vector quantization; Quantization (signal processing); Vector (molecular biology); Computer science; Artificial intelligence; Algorithm; Biology; Genetics","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":[0.002565959,0.001095529,0.001290433,0.001049185,0.0007088053,0.001797606,0.001447238,0.002497936,0.006716891],"category_scores_gemma":[0.01447527,0.0005302724,0.0006607808,0.000971459,0.002651744,0.003524097,0.004561526,0.003686054,0.001069984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009766244,"about_ca_system_score_gemma":0.0007034387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000508034,"about_ca_topic_score_gemma":0.0003746947,"domain_scores_codex":[0.9974649,0.0008977692,0.00009844008,0.000397157,0.0008594925,0.0002823097],"domain_scores_gemma":[0.9925348,0.005041531,0.0004821726,0.00130053,0.0004355753,0.0002054805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002226946,0.00007422754,0.000376898,0.0001088791,0.00007251664,0.00009805991,0.00009011613,0.3913013,0.005537842,0.5164011,0.009582156,0.07613422],"study_design_scores_gemma":[0.00001843379,0.00004849838,0.0001035766,0.00001740806,0.000009585647,0.00005918184,0.00001464771,0.6472582,0.001196506,0.3497436,0.001514827,0.00001558622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02138804,0.0008569108,0.9571287,0.002263506,0.0003289673,0.00007848984,0.0001640346,0.0008573399,0.01693403],"genre_scores_gemma":[0.9257545,0.000586138,0.0571741,0.0009538961,0.0004507455,0.0001480146,0.0002241049,0.0002186907,0.01448974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006716891,"threshold_uncertainty_score":0.02247018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009311214859808124,"score_gpt":0.2604776954554638,"score_spread":0.2511664805956557,"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."}}