{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002515223,0.00115688,0.001058766,0.0005844237,0.000415329,0.001219243,0.001377092,0.001600982,0.002774746],"category_scores_gemma":[0.01211899,0.0004380007,0.0003279258,0.0004970301,0.001336928,0.002609393,0.001930591,0.002254894,0.0005479463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007296221,"about_ca_system_score_gemma":0.001000795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00173083,"about_ca_topic_score_gemma":0.001624407,"domain_scores_codex":[0.9989785,0.000297899,0.00003779175,0.000240551,0.0003334341,0.000111835],"domain_scores_gemma":[0.9952943,0.002984538,0.0003647404,0.0007083298,0.0005148808,0.0001331376],"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":[0.0003335064,0.00005350924,0.0005413744,0.00008428982,0.00005248879,0.00004847897,0.00002517681,0.8904989,0.003726039,0.03220838,0.002435868,0.06999195],"study_design_scores_gemma":[0.000007446939,0.00004308065,0.00005385421,0.000007374041,0.000004713153,0.00002140937,0.000003503032,0.9908793,0.0008596007,0.007761044,0.0003540207,0.000004588936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03473758,0.001064601,0.9570267,0.0005840806,0.0002004599,0.00004798277,0.0001142563,0.0006334913,0.005590915],"genre_scores_gemma":[0.8600818,0.0006798367,0.1320712,0.000332082,0.0001717898,0.00007819095,0.0001999677,0.0001562298,0.00622878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002774746,"threshold_uncertainty_score":0.01330197,"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."}}