{"id":"W4281390966","doi":"10.1145/3488932.3517402","title":"InfoCensor","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mutual information; Computer science; Artificial intelligence; Machine learning; Inference; Interaction information; Deep learning; Adversary; Adversarial system; Bounded function; Softmax function; Mathematics; Computer security","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005352017,0.0001661064,0.0002056884,0.0001309974,0.001008437,0.0001548888,0.007587374,0.00003650241,0.00003645616],"category_scores_gemma":[0.0001546863,0.0001430313,0.00007212057,0.0006218222,0.0001775422,0.0002332082,0.01090198,0.0009498392,0.000004094478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006215602,"about_ca_system_score_gemma":0.0000759235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001604495,"about_ca_topic_score_gemma":0.000001544486,"domain_scores_codex":[0.9986273,0.0001135582,0.0002697387,0.0003405625,0.0004555311,0.0001932944],"domain_scores_gemma":[0.9976589,0.000224231,0.0002991985,0.001537011,0.0002207619,0.00005987956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001641018,0.000178383,0.001198917,0.00001507594,0.00001901952,2.057902e-7,0.002042304,0.0001864158,0.0001047704,0.9842386,0.001414432,0.01058551],"study_design_scores_gemma":[0.0009973578,0.0007615776,0.01174764,0.0000980179,0.00002867989,0.00005205841,0.001169089,0.7744034,0.0005696378,0.1858454,0.02374247,0.000584736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5458163,0.0005744118,0.0352409,0.2160914,0.002862765,0.003107304,0.00009339196,0.001334184,0.1948793],"genre_scores_gemma":[0.9791132,0.0000443772,0.01996235,0.0007045447,0.0000277655,0.0000572347,0.000002247762,0.000009244611,0.0000790973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7983932,"threshold_uncertainty_score":0.9977821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02784295292011382,"score_gpt":0.2723720666151164,"score_spread":0.2445291136950026,"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."}}