{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008157993,0.0006970984,0.0005834378,0.0004674983,0.0003833649,0.001032484,0.001975603,0.001142285,0.002616802],"category_scores_gemma":[0.001771639,0.0004000099,0.0007101389,0.0004134351,0.0008119467,0.001980429,0.001762517,0.001857217,0.0008245808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001206407,"about_ca_system_score_gemma":0.001904462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008616257,"about_ca_topic_score_gemma":0.01287479,"domain_scores_codex":[0.9996245,0.00005236266,0.00002219264,0.00009913382,0.0001285604,0.00007327859],"domain_scores_gemma":[0.9994747,0.0001189655,0.00006345453,0.0001592684,0.0001321742,0.00005148697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002079279,0.0002817329,0.00203356,0.0001395938,0.0001299215,0.0002050092,0.00008686377,0.6418986,0.01018005,0.03712776,0.00920472,0.2985043],"study_design_scores_gemma":[0.000005393723,0.000020345,0.00004987048,0.000004140246,0.000005300245,0.00001561549,0.000003220693,0.9927338,0.001189162,0.005079525,0.0008903854,0.000003176881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01895728,0.0004473966,0.9731962,0.0004866333,0.00005612169,0.0000512984,0.0002305987,0.00374369,0.002830744],"genre_scores_gemma":[0.687313,0.0005927949,0.2992868,0.0005948875,0.00007282456,0.0001507298,0.001216966,0.0002354191,0.0105366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008616257,"threshold_uncertainty_score":0.01713222,"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."}}