Learning to Perturb Hidden Representations for Generalizable Deep Learning

ArXi:2605.29525v1 Announce Type: new Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the input, logit, and label levels have been systematically studied, the intermediate hidden activations, which constitute the bulk of the network's computation, have received no unified perturbation analysis.