{"id":"W3133636092","doi":"10.1109/icpads51040.2020.00084","title":"A Deep Learning Framework Supporting Model Ownership Protection and Traitor Tracing","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Tracing; Traitor tracing; Deep learning; Robustness (evolution); Digital watermarking; TRACE (psycholinguistics); Artificial intelligence; Fingerprint (computing); Collusion; Embedding; Computer security; Process (computing); Focus (optics); Cloud computing; Encryption; Image (mathematics); Public-key cryptography","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":[0.0001812914,0.0001105264,0.0001143044,0.00005460101,0.0002027634,0.0001361191,0.0002197042,0.00008065136,0.000002153628],"category_scores_gemma":[0.0001019165,0.00009332591,0.00004607108,0.0002658507,0.00002393549,0.000569111,0.0000949732,0.0003636008,0.000001118988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007837533,"about_ca_system_score_gemma":0.000008728603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002681742,"about_ca_topic_score_gemma":5.466515e-7,"domain_scores_codex":[0.9991022,0.00004376669,0.0001716601,0.000331295,0.0001237298,0.0002274019],"domain_scores_gemma":[0.999647,0.00003029457,0.00008283048,0.0001133387,0.00002355432,0.0001030394],"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":[0.0000498932,0.00003751574,0.001475674,0.0001853127,0.00002917939,0.00002807605,0.02973991,0.02819596,0.01514902,0.1016608,0.00003534005,0.8234133],"study_design_scores_gemma":[0.00005945981,0.00009578781,0.00007487023,0.00002971866,0.000002637571,0.000007502177,0.0001028084,0.9542522,0.007582955,0.03752666,0.0001185977,0.0001467401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009205625,0.00002756167,0.9871293,0.001866621,0.00002533453,0.000155186,7.745769e-8,0.001041176,0.0005490828],"genre_scores_gemma":[0.6210933,0.000003851688,0.3785506,0.0002773457,0.00003884508,0.00001411885,1.924524e-7,0.000005593025,0.00001612303],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9260563,"threshold_uncertainty_score":0.3805721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03255011505120728,"score_gpt":0.2612869356685947,"score_spread":0.2287368206173874,"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."}}