{"id":"W2909023102","doi":"10.1109/tifs.2019.2894031","title":"Characterizing and Evaluating Adversarial Examples for Offline Handwritten Signature Verification","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Conselho Nacional de Desenvolvimento Científico e Tecnológico; National Science Foundation","keywords":"Computer science; Signature (topology); Adversarial system; Artificial intelligence; Pattern recognition (psychology); Handwriting recognition; Signature recognition; Feature extraction; Speech recognition; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005399348,0.0009129272,0.0008881125,0.0009261584,0.0003555588,0.0009200778,0.001043372,0.001562079,0.0008989992],"category_scores_gemma":[0.0273735,0.0002798479,0.0004616162,0.0003698455,0.001361583,0.001900117,0.001407251,0.0009298801,0.0003305937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001075723,"about_ca_system_score_gemma":0.0005978519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009678827,"about_ca_topic_score_gemma":0.0009176492,"domain_scores_codex":[0.9956637,0.001809683,0.0002749975,0.0006763797,0.001308618,0.0002667035],"domain_scores_gemma":[0.9706391,0.02250466,0.002344586,0.002856307,0.001174518,0.0004808673],"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":[0.001316597,0.0003068868,0.006338254,0.0002513301,0.0001448982,0.0002109041,0.00008849936,0.8972021,0.01799439,0.003807153,0.001236317,0.07110268],"study_design_scores_gemma":[0.00001654695,0.0002196824,0.001059142,0.00001515308,0.00001348061,0.000117667,0.00002108477,0.9852824,0.01188181,0.001094376,0.0002680531,0.00001045456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7775654,0.001619418,0.2154035,0.0003764407,0.0001452331,0.0002860747,0.0003487163,0.001239395,0.003015897],"genre_scores_gemma":[0.9646731,0.000134732,0.03417819,0.00005717068,0.00002718127,0.00003858973,0.0003130913,0.00004581551,0.0005321697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005399348,"threshold_uncertainty_score":0.0285548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01713105310537766,"score_gpt":0.2556298412927902,"score_spread":0.2384987881874125,"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."}}