{"id":"W4297691576","doi":"10.1007/s10994-022-06212-w","title":"Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Robustness (evolution); Artificial neural network; Solver; Algorithm; Linear programming; Integer programming; Scalability; Machine learning; Artificial intelligence; Programming language; Database","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001734923,0.0003731235,0.0003726093,0.0002389452,0.001826204,0.0004137832,0.0008156601,0.0001016136,0.0001783971],"category_scores_gemma":[0.0001696883,0.0004111111,0.00009155775,0.0008835448,0.00007733674,0.001241742,0.0008246914,0.001499887,0.000004708365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000144422,"about_ca_system_score_gemma":0.00006178239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001955919,"about_ca_topic_score_gemma":0.000007016342,"domain_scores_codex":[0.9964378,0.0007983021,0.0005302205,0.0009301168,0.0006396333,0.0006639519],"domain_scores_gemma":[0.9985351,0.0001668696,0.0004817272,0.0004890618,0.0001286247,0.0001986305],"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":[0.00002800442,0.00003145326,0.001943687,0.000009915747,0.00001973552,0.00002244137,0.0007772754,0.7465177,0.0001951249,0.0006944568,0.00004185687,0.2497184],"study_design_scores_gemma":[0.0007890975,0.0002652006,0.0007259107,0.00001369088,0.00002768888,0.00009633054,0.0003155933,0.9913703,0.00005871004,0.0001069188,0.005771376,0.0004591423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01981329,0.0001768015,0.9768093,0.0004154862,0.001476809,0.0004089117,0.000001323595,0.0006796634,0.000218415],"genre_scores_gemma":[0.7390056,0.000007797985,0.2593715,0.0001584713,0.0006536735,0.00007717532,0.000203416,0.00006914875,0.0004531551],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7191923,"threshold_uncertainty_score":0.9998341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01773640680379212,"score_gpt":0.2676250028311039,"score_spread":0.2498885960273117,"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."}}