{"id":"W4231465774","doi":"10.36227/techrxiv.13650059","title":"SecureDL: A privacy preserving deep learning model for image recognition over cloud","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Chaos-based Image/Signal Encryption","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Encryption; Homomorphic encryption; Cloud computing; Block (permutation group theory); Cryptography; Server; Flexibility (engineering); Secure multi-party computation; Information privacy; Computer security; Artificial intelligence; Theoretical computer science; Computer network; Operating system","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":[0.0007137634,0.0003593714,0.0005227577,0.0002783973,0.0002540178,0.0008482065,0.001391724,0.0006697107,0.001689008],"category_scores_gemma":[0.001218265,0.0002466478,0.0005518013,0.0003724001,0.0006479094,0.001604161,0.001528443,0.001501255,0.0006063542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081194,"about_ca_system_score_gemma":0.001336396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004419937,"about_ca_topic_score_gemma":0.004137643,"domain_scores_codex":[0.9995727,0.00007925834,0.00002636341,0.00008422608,0.0001592819,0.00007822096],"domain_scores_gemma":[0.9996401,0.00008586106,0.00005991799,0.000116583,0.00006790997,0.00002954964],"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":[0.0005328798,0.0002639731,0.001524626,0.00009112623,0.00007956414,0.0002202036,0.0000784123,0.743158,0.015773,0.05506967,0.005779628,0.177429],"study_design_scores_gemma":[0.000005803888,0.00001770095,0.00004648979,0.000001688097,0.000002235013,0.00001232401,0.000002706936,0.9941081,0.00142936,0.003961158,0.0004093129,0.000003226366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02251211,0.0001832682,0.9744041,0.000374312,0.00003664218,0.00004266317,0.0001736385,0.0009376351,0.001335507],"genre_scores_gemma":[0.8368465,0.0004007052,0.1524352,0.0003707383,0.00005592395,0.0001323321,0.0006374967,0.0001354083,0.008985632],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004419937,"threshold_uncertainty_score":0.008788407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03991579275938122,"score_gpt":0.2847516694165371,"score_spread":0.2448358766571559,"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."}}