Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations. (arXiv:2212.03095v1 [cs.CV])

Interpreting neural network classifiers using gradient-based saliency maps
has been extensively studied in the deep learning literature. While the
existing algorithms manage to achieve satisfactory performance in application
to standard image recognition datasets, recent works demonstrate the
vulnerability of widely-used gradient-based interpretation schemes to
norm-bounded perturbations adversarially designed for every individual input
sample. However, such adversarial perturbations are commonly designed using the
knowledge of an input sample, and hence perform sub-optimally in application to
an unknown or constantly changing data …

adversarial networks neural networks