{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004955891,0.0005874089,0.0004401204,0.0007516222,0.0003823437,0.001432755,0.0006977142,0.0007379327,0.009245496],"category_scores_gemma":[0.001322717,0.0002976975,0.0005509508,0.0007629301,0.0007115236,0.00229874,0.001890778,0.001071256,0.004281547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003222785,"about_ca_system_score_gemma":0.0003409697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004769383,"about_ca_topic_score_gemma":0.0006026955,"domain_scores_codex":[0.9995674,0.0001054607,0.00002060922,0.00006994935,0.0001922035,0.00004432969],"domain_scores_gemma":[0.9996004,0.0001114086,0.00003515015,0.0001605198,0.00006935758,0.00002320693],"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":[0.0004821028,0.00019772,0.0004585767,0.0002627232,0.00006377121,0.0002452316,0.0002123726,0.0233902,0.1092506,0.1057857,0.01710901,0.742542],"study_design_scores_gemma":[0.00008119948,0.0001905697,0.0004520502,0.00005555195,0.00003552769,0.0006997052,0.00006771922,0.7483423,0.1196129,0.06816339,0.06223839,0.00006067546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003912127,0.0003386035,0.9867175,0.00009320676,0.0000924242,0.00003667699,0.0001155029,0.00539239,0.003301619],"genre_scores_gemma":[0.2528097,0.0007907695,0.7120417,0.000200806,0.0001384823,0.000161861,0.0009478978,0.001427921,0.03148095],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009245496,"threshold_uncertainty_score":0.03092921,"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."}}