{"id":"W4390533396","doi":"10.1109/tsc.2023.3349298","title":"Privacy-Preserving Convolutional Neural Network Classification Scheme With Multiple Keys","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Key Research and Development Projects of Shaanxi Province; National College Students Innovation and Entrepreneurship Training Program; Innovation Scientists and Technicians Troop Construction Projects of Henan Province; Natural Science Foundation of Henan Province; National Natural Science Foundation of China","keywords":"Computer science; Homomorphic encryption; Convolutional neural network; Activation function; Cryptosystem; Information privacy; Encryption; Functional encryption; Public-key cryptography; Theoretical computer science; Ciphertext; Artificial intelligence; Data mining; Computer security; Artificial neural network","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":[0.002186861,0.0007515047,0.001038922,0.0007480636,0.001500152,0.002623468,0.002115317,0.001676326,0.003848981],"category_scores_gemma":[0.005364392,0.0004581677,0.001205755,0.001319498,0.001821227,0.005562669,0.005035155,0.003114686,0.001251397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002722412,"about_ca_system_score_gemma":0.003093632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001280667,"about_ca_topic_score_gemma":0.001012044,"domain_scores_codex":[0.9957827,0.0007997053,0.0003911776,0.0008586971,0.001314346,0.000853406],"domain_scores_gemma":[0.996271,0.0007934552,0.0004593562,0.001948947,0.0003709005,0.0001563136],"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":[0.001728294,0.000371852,0.002371747,0.0003935104,0.0001855043,0.001121086,0.0007892778,0.09177805,0.04901347,0.6594533,0.01339248,0.1794015],"study_design_scores_gemma":[0.0003309907,0.0002959828,0.0008129316,0.00009106794,0.0001294364,0.00101941,0.0001314642,0.6881976,0.07114777,0.2170162,0.02068823,0.0001388875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06544209,0.0005123355,0.9140571,0.001930868,0.0002750695,0.0005280136,0.0006603881,0.002856976,0.01373719],"genre_scores_gemma":[0.9208416,0.0003094813,0.0695076,0.0003852714,0.00008349964,0.0004702669,0.0004198521,0.00008432719,0.007898143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003848981,"threshold_uncertainty_score":0.01975256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02040361260747392,"score_gpt":0.2485578780755709,"score_spread":0.228154265468097,"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."}}