{"id":"W4286354782","doi":"10.21123/bsj.2022.6550","title":"Retrieving Encrypted Images Using Convolution Neural Network and Fully Homomorphic Encryption","year":2022,"lang":"en","type":"article","venue":"Baghdad Science Journal","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Homomorphic encryption; Convolutional neural network; Artificial intelligence; Image retrieval; Deep learning; Encryption; Hamming distance; Image (mathematics); Pattern recognition (psychology); Computer vision; Computer security; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002858465,0.000155092,0.0001667208,0.0004399899,0.003982343,0.0007243754,0.001194407,0.00003177525,0.00001352475],"category_scores_gemma":[0.0000677556,0.0001478925,0.00007068906,0.00218499,0.0004503982,0.002609434,0.0008257497,0.0006068448,6.641772e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002041439,"about_ca_system_score_gemma":0.0002124518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008421555,"about_ca_topic_score_gemma":4.701147e-7,"domain_scores_codex":[0.9976113,0.0001901849,0.000337594,0.0004287678,0.0008267832,0.0006053214],"domain_scores_gemma":[0.998957,0.00005046541,0.000321697,0.0003043849,0.0001803058,0.0001861696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002000291,0.0002578073,0.1205176,0.00004680461,0.00005006518,0.0008361949,0.004256472,0.06107438,0.5898918,0.05280837,0.0025132,0.1675473],"study_design_scores_gemma":[0.0009956494,0.001019321,0.07968567,0.0001484306,0.00003723734,0.01430321,0.0003887176,0.778492,0.008564439,0.1122009,0.003036604,0.001127849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4643306,0.0005675892,0.5334519,0.0003734523,0.000837812,0.0001190755,0.000001222621,0.0002284439,0.00008999212],"genre_scores_gemma":[0.880553,0.00007293659,0.1190276,0.0001748733,0.0001490193,0.000004816398,3.170096e-7,0.000008301971,0.000009177972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7174176,"threshold_uncertainty_score":0.9973143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02002711165804696,"score_gpt":0.2563887789247981,"score_spread":0.2363616672667511,"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."}}