Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense. (arXiv:2207.13036v4 [cs.LG] UPDATED)

Deep neural networks (DNNs) are known to be vulnerable to adversarial
examples that are crafted with imperceptible perturbations, i.e., a small
change in an input image can induce a mis-classification, and thus threatens
the reliability of deep learning based deployment systems. Adversarial training
(AT) is often adopted to improve robustness through training a mixture of
corrupted and clean data. However, most of AT based methods are ineffective in
dealing with transferred adversarial examples which are generated to fool a
wide …

adversarial defense input