{"id":"W3165255230","doi":"10.1007/s11042-023-15371-4","title":"Robust watermarking using diffusion of logo into auto-encoder feature maps","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Digital watermarking; Computer science; Watermark; Robustness (evolution); Artificial intelligence; Computer vision; Image processing; Convolutional neural network; Embedding; Pattern recognition (psychology); Image (mathematics)","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":[0.000150547,0.0001274113,0.0001561286,0.0001643758,0.000268527,0.00008197577,0.0003922462,0.00009218838,0.000001450616],"category_scores_gemma":[0.00001100751,0.0001076619,0.00005420961,0.000610696,0.0000957022,0.000339477,0.0003201491,0.0001255816,0.000004090373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001436059,"about_ca_system_score_gemma":0.00001626498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001949757,"about_ca_topic_score_gemma":0.000002617672,"domain_scores_codex":[0.9991155,0.00002590034,0.0001858891,0.0003206758,0.0001426335,0.0002094082],"domain_scores_gemma":[0.9992694,0.0001042605,0.00009536303,0.0004066273,0.00005665331,0.00006765441],"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":[0.000009740452,0.0001233364,0.006700582,0.0001752504,0.00003369186,0.000009201312,0.003442934,0.0009105401,0.1766889,0.01153018,0.001109226,0.7992665],"study_design_scores_gemma":[0.0006777321,0.00006032381,0.01903076,0.0002244546,0.00003625244,0.00002542326,0.0001862314,0.8269765,0.04554233,0.05042163,0.05609907,0.0007192513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02364817,0.0001108238,0.9746372,0.0004637177,0.00006743958,0.0003937574,0.00002388,0.0004846354,0.0001704543],"genre_scores_gemma":[0.431533,0.000234345,0.5676766,0.0000761569,0.00009544312,0.0001924102,0.00007898241,0.00001602099,0.00009702505],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.826066,"threshold_uncertainty_score":0.4390325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03812165882138487,"score_gpt":0.2727811177863756,"score_spread":0.2346594589649907,"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."}}