{"id":"W4405203783","doi":"10.1145/3658644.3690373","title":"TabularMark: Watermarking Tabular Datasets for Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Precursory Research for Embryonic Science and Technology; Japan Society for the Promotion of Science; Core Research for Evolutional Science and Technology; National Natural Science Foundation of China","keywords":"Digital watermarking; Computer science; Robustness (evolution); USable; Data mining; Artificial intelligence; Machine learning; Watermark; Image (mathematics)","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":[0.005739608,0.000940368,0.0008224819,0.001610572,0.0009122925,0.004135256,0.002111232,0.002026665,0.008033545],"category_scores_gemma":[0.0334582,0.0004976829,0.0008233069,0.002490147,0.002460726,0.01088119,0.005022134,0.002399204,0.003547235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007762552,"about_ca_system_score_gemma":0.001194798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003915148,"about_ca_topic_score_gemma":0.0004354746,"domain_scores_codex":[0.9952202,0.001528401,0.0005826906,0.0007688469,0.001596665,0.0003032121],"domain_scores_gemma":[0.9762489,0.005914112,0.002194339,0.01407629,0.001332819,0.0002335382],"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":[0.001677615,0.000247418,0.002904509,0.001256091,0.0002549447,0.0004776258,0.0007480151,0.03457665,0.04151981,0.2871023,0.07617722,0.5530577],"study_design_scores_gemma":[0.0003283624,0.0003900269,0.001252169,0.0006123897,0.00009080031,0.000951043,0.0002889616,0.2214886,0.15204,0.4414978,0.1808528,0.0002069689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01339346,0.001936151,0.9548089,0.002184405,0.0006445014,0.0002718757,0.004269224,0.01588487,0.006606618],"genre_scores_gemma":[0.4567466,0.003355821,0.5096052,0.002784667,0.0008230809,0.0009856748,0.01244484,0.00300914,0.01024493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008033545,"threshold_uncertainty_score":0.03035432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02738614540602429,"score_gpt":0.2860790419800042,"score_spread":0.2586928965739799,"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."}}