{"id":"W4399754920","doi":"10.1016/j.ajoint.2024.100043","title":"Hidden in plain sight: AI-driven steganography and watermarking for secure transmission of ophthalmic data","year":2024,"lang":"en","type":"article","venue":"AJO International","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Digital watermarking; Steganography; Sight; Transmission (telecommunications); Computer science; Artificial intelligence; Computer security; Computer vision; Embedding; Telecommunications; Optics; Image (mathematics); Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000231717,0.0001147289,0.0001240314,0.0004290422,0.00003875743,0.0001421511,0.001060783,0.00006273195,0.000005707168],"category_scores_gemma":[0.000007695086,0.00009741043,0.0000722289,0.0002301354,0.00004713725,0.001209532,0.0002711449,0.0001300268,3.9912e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000144664,"about_ca_system_score_gemma":0.00002374811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001056751,"about_ca_topic_score_gemma":0.000004570258,"domain_scores_codex":[0.9989833,0.00002474737,0.0002507806,0.0004034427,0.0001896327,0.0001480826],"domain_scores_gemma":[0.9994656,0.0001203585,0.00004345394,0.0002957068,0.00004131427,0.00003351077],"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":[0.0002297882,0.000291277,0.02075405,0.0008765783,0.0004854637,0.0002889011,0.008405747,0.0001460987,0.05204369,0.2129504,0.003305576,0.7002224],"study_design_scores_gemma":[0.001160217,0.0002625981,0.005488907,0.001825509,0.00003283555,0.0001728588,0.00006214831,0.6546398,0.04224208,0.1817956,0.1116762,0.0006412379],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06060939,0.0008818985,0.934541,0.00213133,0.0005545661,0.0003247947,0.0001173771,0.0002057332,0.0006339516],"genre_scores_gemma":[0.9319816,0.0000785407,0.06768645,0.00005564105,0.00004988877,0.00002076123,0.00008856301,0.000009605823,0.00002894021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8713722,"threshold_uncertainty_score":0.3972282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382149994990437,"score_gpt":0.3051555085599238,"score_spread":0.2813340086100194,"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."}}