{"id":"W4386597257","doi":"10.1109/icip49359.2023.10221905","title":"Detecting Stable Diffusion Generated Images Using Frequency Artifacts: A Case Study on Disney-Style Art","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Realm; Animation; Artificial intelligence; Domain (mathematical analysis); Diffusion; Style (visual arts); Frequency domain; Property (philosophy); Deep learning; Computer vision; Computer graphics (images); Visual arts; Art; 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":[0.0005567298,0.0002540754,0.0002487551,0.0002187755,0.0007037199,0.0004823084,0.0003449071,0.00005306903,0.00008000675],"category_scores_gemma":[0.0001161535,0.000204926,0.00007443339,0.00131477,0.00002762622,0.0006938652,0.0003464699,0.0001664869,0.0002490454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007262854,"about_ca_system_score_gemma":0.00005064367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009639226,"about_ca_topic_score_gemma":0.0002117049,"domain_scores_codex":[0.9978657,0.0002847917,0.0003355239,0.0006672704,0.0003199812,0.0005266811],"domain_scores_gemma":[0.9988055,0.000190027,0.0001066267,0.0006339223,0.0001223232,0.000141561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003105274,0.001414806,0.01040355,0.00002772565,0.0002432523,0.01888234,0.00710812,0.07436381,0.7993614,0.000380702,0.005623852,0.0821594],"study_design_scores_gemma":[0.0005768533,0.0003545938,0.001279856,0.00002827311,0.00002541307,0.0002217957,0.003077557,0.948982,0.04467797,0.0001849883,0.000124976,0.0004656965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6274881,0.00001315231,0.3707096,0.00009722734,0.000313025,0.0002879123,0.000002314928,0.0003440949,0.000744518],"genre_scores_gemma":[0.9762129,0.000005571893,0.02271165,0.0001262123,0.0001492617,0.00002066228,0.000002565273,0.00002337624,0.0007477886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8746182,"threshold_uncertainty_score":0.835664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04495644788568594,"score_gpt":0.2816561982229749,"score_spread":0.2366997503372889,"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."}}