{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001818021,0.0004563283,0.0008007018,0.0005982795,0.0007788096,0.001015562,0.001832151,0.001165812,0.001404648],"category_scores_gemma":[0.004370913,0.0002385829,0.0008413786,0.0005788516,0.0009252125,0.002099871,0.001971708,0.001407265,0.0005267135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006832829,"about_ca_system_score_gemma":0.0008060306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001103896,"about_ca_topic_score_gemma":0.0008224475,"domain_scores_codex":[0.9985405,0.0004509756,0.00009634589,0.0003411848,0.0004243677,0.0001466345],"domain_scores_gemma":[0.9982764,0.0005703582,0.0001817148,0.0006141154,0.0002820515,0.00007545897],"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":[0.0007565859,0.0004885726,0.002018922,0.0001140589,0.0001235882,0.0004844946,0.0004851294,0.2626866,0.0328067,0.03971266,0.003402431,0.6569203],"study_design_scores_gemma":[0.00001828063,0.0000828352,0.0002535864,0.00001023358,0.00001473338,0.0002243985,0.00004163905,0.9680023,0.01332669,0.01665688,0.001350018,0.00001853035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01950611,0.00008368857,0.9788107,0.0001062641,0.00002719858,0.00004857159,0.00002331615,0.000506638,0.0008875534],"genre_scores_gemma":[0.6866873,0.0001270351,0.3098532,0.0001755649,0.00003349114,0.0001074634,0.0001070763,0.0000469675,0.002862011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001832151,"threshold_uncertainty_score":0.009614706,"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."}}