{"id":"W4415595958","doi":"10.1016/j.future.2025.108220","title":"Robust DCNN: The impact of approximate multipliers in defending against adversarial attacks","year":2025,"lang":"en","type":"article","venue":"Future Generation Computer Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Instituto Tecnológico de Costa Rica","keywords":"Robustness (evolution); Adversarial system; Computation; Optimization problem; Ambiguity; Lagrange multiplier; Metric (unit); Pareto principle","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":[0.0009300682,0.0002841989,0.0004052609,0.0003567271,0.0003170932,0.0003338107,0.001159644,0.0001773475,0.000002401792],"category_scores_gemma":[0.00003890414,0.0002050596,0.0001908948,0.0008269463,0.0000464915,0.0004595026,0.0004230704,0.0003955511,0.00000441786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002837339,"about_ca_system_score_gemma":0.0002052431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002333401,"about_ca_topic_score_gemma":0.00003552208,"domain_scores_codex":[0.9975477,0.0005456043,0.0006649014,0.0005471792,0.0003354604,0.0003590845],"domain_scores_gemma":[0.9985054,0.0001589741,0.0003401822,0.0007884839,0.0001507183,0.00005629585],"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":[0.00001123223,0.0000301273,0.002556971,0.00003523009,0.00006657501,0.000005718845,0.001493873,0.9675326,0.0003523574,0.009510234,0.01322557,0.005179562],"study_design_scores_gemma":[0.0008386986,0.0000382606,0.001804394,0.00008216786,0.000007168542,0.0000063927,0.0001230186,0.9950412,0.00007609439,0.00000893686,0.001787026,0.0001866579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01604106,0.0003439665,0.9457984,0.0003504255,0.03629355,0.0005575479,0.000003880924,0.0001167823,0.0004944018],"genre_scores_gemma":[0.9110807,0.00001668263,0.06570501,0.0001537613,0.02278425,0.00005955894,0.00004400769,0.00002472237,0.0001313094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8950396,"threshold_uncertainty_score":0.8362087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02295755602172824,"score_gpt":0.276162746961469,"score_spread":0.2532051909397408,"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."}}