Exploring the Connection between Robust and Generative Models. (arXiv:2304.04033v1 [cs.LG])

We offer a study that connects robust discriminative classifiers trained with
adversarial training (AT) with generative modeling in the form of Energy-based
Models (EBM). We do so by decomposing the loss of a discriminative classifier
and showing that the discriminative model is also aware of the input data
density. Though a common assumption is that adversarial points leave the
manifold of the input data, our study finds out that, surprisingly, untargeted
adversarial points in the input space are very likely …

adversarial aware data energy generative hidden input loss manifold modeling offer space study training under