{"id":"W4389998928","doi":"10.18280/mmep.100642","title":"Enhancing Privacy Protection in Online Federated Learning: A Method for Secure Face Image De-Identification Using a Modified Diffie-Hellman Algorithm","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Identification (biology); Computer science; Image (mathematics); Algorithm; Face (sociological concept); Privacy protection; Diffie–Hellman key exchange; Computer security; Artificial intelligence; Encryption; Sociology; Public-key cryptography; Key exchange","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008184068,0.0001519177,0.0002309625,0.0002696433,0.0001327177,0.0002539786,0.0001208964,0.00009247455,0.000001091852],"category_scores_gemma":[0.0001221988,0.0001499281,0.00006147732,0.000611301,0.000007891351,0.0002077013,0.00005549167,0.0002270169,0.000004455416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000446134,"about_ca_system_score_gemma":0.00001689081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002168367,"about_ca_topic_score_gemma":0.000001452879,"domain_scores_codex":[0.9988133,0.00004585013,0.0003591096,0.0003352605,0.0001352316,0.0003112488],"domain_scores_gemma":[0.9995407,0.0001285383,0.00007019577,0.0001208033,0.00006274719,0.00007697399],"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":[0.000001265956,0.00004172619,3.1861e-7,0.000422956,0.0000147789,0.000001229825,0.001521578,0.9499566,0.04005117,0.0004063666,5.851871e-7,0.007581452],"study_design_scores_gemma":[0.0002363637,0.00002004429,0.000001900762,0.0002607003,0.00001491093,0.000009630945,0.0001147462,0.9861031,0.004131781,0.00892133,0.00001351683,0.0001719506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04054245,0.0000253949,0.9584572,0.0001981353,0.00002583691,0.0003695112,0.000002242238,0.0003758701,0.000003399188],"genre_scores_gemma":[0.2691219,0.00002535415,0.7305927,0.000005539631,0.00002049607,0.00009902183,0.00001502888,0.00002263992,0.00009729328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2285795,"threshold_uncertainty_score":0.6113889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04649057917362562,"score_gpt":0.2818282909929391,"score_spread":0.2353377118193135,"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."}}