{"id":"W2102511552","doi":"10.1109/tsp.2003.812753","title":"Detection of LSB steganography via sample pair analysis","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":522,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Least significant bit; Steganalysis; Steganography; Robustness (evolution); Computer science; Embedding; Digital watermarking; Artificial intelligence; Sample (material); Pattern recognition (psychology); Mathematics; Algorithm; Statistics; Image (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":[0.0002836325,0.0001866227,0.000255512,0.0009925284,0.000364509,0.0000794151,0.0003186025,0.00009404573,0.00001126414],"category_scores_gemma":[0.000002553842,0.0001772296,0.0003381742,0.003489377,0.00008626413,0.0007004216,0.000001383649,0.0002219291,0.000001121825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002510847,"about_ca_system_score_gemma":0.00003305667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001978586,"about_ca_topic_score_gemma":0.00001719348,"domain_scores_codex":[0.9985943,0.0001212699,0.000339745,0.0003848663,0.000302442,0.0002573919],"domain_scores_gemma":[0.999165,0.0001178335,0.000174396,0.0003293315,0.0001397828,0.00007365346],"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":[0.00006222012,0.0004541928,0.0005034861,0.0001137475,0.0004208595,0.00000528348,0.001040466,0.02763462,0.07482763,0.0003874805,0.000002587387,0.8945475],"study_design_scores_gemma":[0.0001886434,0.0002034477,0.0001045004,0.00004281311,0.0001719502,0.000008095868,0.00003760427,0.04719997,0.943139,0.008378273,0.0002588306,0.0002669391],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007154122,0.00008667744,0.9920334,0.00001687938,0.00007720479,0.0001131285,0.000004995578,0.0003794953,0.0001341462],"genre_scores_gemma":[0.9057118,0.000008523086,0.09418219,0.00004448338,0.000007527602,0.00002555026,5.934773e-7,0.00001066049,0.000008706202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8985577,"threshold_uncertainty_score":0.7227213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0149777103869064,"score_gpt":0.2444535555597215,"score_spread":0.2294758451728151,"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."}}