{"id":"W4395690619","doi":"10.22214/ijraset.2024.60765","title":"Exposing Fake Faces Through Deep Neural Networks Combining Content and Trace Feature Extractors","year":2024,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"TRACE (psycholinguistics); Computer science; Feature (linguistics); Content (measure theory); Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Mathematics; Philosophy","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001374385,0.00009967832,0.0001066202,0.001126973,0.0001714639,0.001244119,0.0008237749,0.00009016428,3.40655e-7],"category_scores_gemma":[0.0002898453,0.00008666395,0.00001849072,0.001060931,0.0003789229,0.0009343329,0.0003331469,0.0007942878,5.777892e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839134,"about_ca_system_score_gemma":0.00005338962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003508433,"about_ca_topic_score_gemma":0.000003741533,"domain_scores_codex":[0.9984158,0.000005856285,0.0001731525,0.0003422323,0.0006180506,0.0004448826],"domain_scores_gemma":[0.9993317,0.0002410477,0.00002697529,0.0001059212,0.0002076735,0.00008664427],"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":[0.00001593734,0.0000169081,0.00006849078,0.00001876724,0.0000195757,0.0001126945,0.0005548959,0.004761482,0.02777935,0.2464638,0.00006221409,0.7201259],"study_design_scores_gemma":[0.0002341342,0.0001152046,0.0001764961,0.0001090492,0.000001126751,0.0007705194,0.0003803663,0.9727855,0.003204547,0.01845498,0.003656015,0.0001120042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3094206,0.002116604,0.6764514,0.007919035,0.003305749,0.0002956582,0.000001278775,0.0002449838,0.0002446898],"genre_scores_gemma":[0.983462,0.0001200178,0.01625349,0.0000214782,0.00008928183,0.00003557152,3.213553e-7,0.000008331106,0.000009557176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680241,"threshold_uncertainty_score":0.9997927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06297834367051158,"score_gpt":0.3483267855278048,"score_spread":0.2853484418572932,"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."}}