{"id":"W4404672157","doi":"10.1007/978-3-031-73024-5_8","title":"LaWa: Using Latent Space for In-Generation Image Watermarking","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada); University of British Columbia","funders":"","keywords":"Computer science; Digital watermarking; Computer vision; Image (mathematics); Artificial intelligence; Space (punctuation); Computer graphics (images); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000858506,0.0004948482,0.0004476873,0.001289265,0.0002285837,0.0007791223,0.001696381,0.0002879492,0.000001825504],"category_scores_gemma":[0.00002166176,0.0004417209,0.000179255,0.0006060358,0.0003359525,0.0009187962,0.0009367385,0.0006080252,0.000004415084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003902168,"about_ca_system_score_gemma":0.0001782422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001999704,"about_ca_topic_score_gemma":0.00006525462,"domain_scores_codex":[0.9968247,0.00002262961,0.0005128041,0.001467748,0.0004970447,0.0006751036],"domain_scores_gemma":[0.9985563,0.0001590303,0.0001818567,0.0008604375,0.0001555383,0.0000868343],"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":[0.00003356854,0.00008797892,0.0002113223,0.0006173922,0.00005125114,0.0007058533,0.003979475,0.08705911,0.04492165,0.2487158,0.00006947004,0.6135471],"study_design_scores_gemma":[0.0001304147,0.00007349603,0.000009594492,0.000625645,0.000007340536,0.00004280486,6.150472e-8,0.6511047,0.02264543,0.3238399,0.00102898,0.0004915554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002907393,0.0004442503,0.9952547,0.0005084106,0.001916579,0.0006246801,0.000007120881,0.0002860165,0.000667529],"genre_scores_gemma":[0.1405768,0.0000529515,0.8582424,0.0003413735,0.0005244641,0.00002568912,0.000009586893,0.00004751627,0.0001792129],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6130556,"threshold_uncertainty_score":0.9998035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02949825161962789,"score_gpt":0.2752053984943558,"score_spread":0.2457071468747279,"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."}}