{"id":"W4402593024","doi":"10.1109/tifs.2024.3463547","title":"LiDiNet: A Lightweight Deep Invertible Network for Image-in-Image Steganography","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Computer science; Steganography; Image (mathematics); Artificial intelligence; Computer vision; Steganography tools","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":[0.0002985903,0.000504756,0.0003743462,0.0003444625,0.0001936032,0.0003308182,0.0008976404,0.0005036824,0.00145975],"category_scores_gemma":[0.0006598017,0.0002116653,0.0003197427,0.0002122113,0.0004056969,0.0008554653,0.001008199,0.0008629601,0.0004994998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000399811,"about_ca_system_score_gemma":0.0004162712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001444819,"about_ca_topic_score_gemma":0.003168986,"domain_scores_codex":[0.9998435,0.0000215162,0.0000080323,0.00003348637,0.00006267794,0.00003077771],"domain_scores_gemma":[0.9998317,0.0000551368,0.00002498694,0.00003421211,0.00003804735,0.00001587222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004297702,0.0002145449,0.001873716,0.0003026813,0.0001475603,0.0004141406,0.0001489047,0.220891,0.2213061,0.018678,0.005771328,0.5298223],"study_design_scores_gemma":[0.00001870241,0.0001483482,0.0004430995,0.00001763718,0.00002733496,0.0001989227,0.00001661915,0.9478563,0.0420295,0.003513913,0.005708816,0.0000207694],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04151455,0.0007339923,0.9500502,0.0001997059,0.00008740609,0.00007030783,0.0001309181,0.002511846,0.004701006],"genre_scores_gemma":[0.6754947,0.0007892282,0.3127888,0.0003530282,0.00005974895,0.0001431545,0.0005964224,0.0001831148,0.009591859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00145975,"threshold_uncertainty_score":0.004883349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007437965867502502,"score_gpt":0.230467002183926,"score_spread":0.2230290363164235,"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."}}