{"id":"W2937447982","doi":"10.1109/icassp.2019.8682202","title":"Attacks on Digital Watermarks for Deep Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Digital watermarking; Computer science; Watermark; Artificial intelligence; Artificial neural network; Countermeasure; Deep learning; Embedding; Property (philosophy); Deep neural networks; Task (project management); Scheme (mathematics); Data mining; Machine learning; Computer security; Image (mathematics); 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":[0.000129586,0.000141618,0.0001422975,0.00004854942,0.0000861192,0.0003214078,0.0007656166,0.00006962825,0.00005707544],"category_scores_gemma":[0.00004278977,0.0001110569,0.00008850652,0.0001118737,0.00001684159,0.0007149968,0.0002947942,0.000196324,0.0001191337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002663158,"about_ca_system_score_gemma":0.000007333201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003187449,"about_ca_topic_score_gemma":0.000001074988,"domain_scores_codex":[0.9989311,0.00002293049,0.0001520477,0.0003774627,0.0001645682,0.0003518694],"domain_scores_gemma":[0.9991131,0.0002587816,0.00005382662,0.0004683079,0.00003764507,0.00006837678],"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":[0.00002819316,0.00002216846,0.005043441,0.000006752336,0.00001142936,0.000004162006,0.000098152,0.8612382,0.000007958835,0.02362475,0.000510162,0.1094046],"study_design_scores_gemma":[0.0004087075,0.0001376136,0.0007429657,0.000004260914,0.000001679111,0.000004812661,0.000008977319,0.9957713,0.00002231182,0.0004645036,0.002267099,0.0001657555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01621963,0.000006201288,0.9676709,0.0005934939,0.001143182,0.0002617536,4.846282e-7,0.0002214546,0.01388296],"genre_scores_gemma":[0.9842232,2.767953e-7,0.01286419,0.0007275814,0.0001892844,0.000009870145,0.000008828518,0.00001537627,0.001961415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680035,"threshold_uncertainty_score":0.4528769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007538449835468789,"score_gpt":0.2413116925341822,"score_spread":0.2337732426987134,"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."}}