May the Noise be with you: Adversarial Training without Adversarial Examples. (arXiv:2312.08877v1 [cs.LG])

In this paper, we investigate the following question: Can we obtain
adversarially-trained models without training on adversarial examples? Our
intuition is that training a model with inherent stochasticity, i.e.,
optimizing the parameters by minimizing a stochastic loss function, yields a
robust expectation function that is non-stochastic. In contrast to related
methods that introduce noise at the input level, our proposed approach
incorporates inherent stochasticity by embedding Gaussian noise within the
layers of the NN model at training time. We model …

adversarial function intuition loss may noise non question training