3 papers
stat.ML2026
On damage of interpolation to adversarial robustness in regression
Jingfu Peng, Yuhong Yang
Deep neural networks (DNNs) typically involve a large number of parameters and are trained to achieve zero or near-zero training error. Despite such interpolation, they often exhib…
stat.ML2025
Adversarial learning for nonparametric regression: Minimax rate and adaptive estimation
Jingfu Peng, Yuhong Yang
Despite tremendous advancements of machine learning models and algorithms in various application domains, they are known to be vulnerable to subtle, natural or intentionally crafte…
math.ST2025
Minimax rates of convergence for nonparametric regression under adversarial attacks
Jingfu Peng, Yuhong Yang
Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrad…