Search Results for author:
Found 4 papers, 0 papers with code
FG-UAP: Feature-Gathering Universal Adversarial Perturbation
Deep Neural Networks (DNNs) are susceptible to elaborately designed perturbations, whether such perturbations are dependent or independent of images.
Dominant Patterns: Critical Features Hidden in Deep Neural Networks
As the name suggests, for a natural image, if we add the dominant pattern of a DNN to it, the output of this DNN is determined by the dominant pattern instead of the original image, i. e., DNN's prediction is the same with the dominant pattern's.
Measuring the Transferability of $\ell_\infty$ Attacks by the $\ell_2$ Norm
Deep neural networks could be fooled by adversarial examples with trivial differences to original samples.
HRFA: High-Resolution Feature-based Attack
Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input.
