Feature autoencoder for detecting adversarial examples
Sign Up to like & getrecommendations! Published in 2022 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.22889
Abstract: Deep neural networks (DNNs) have gained widespread adoption in computer vision. Unfortunately, state‐of‐the‐art DNNs are vulnerable to adversarial example (AE) attacks, where an adversary introduces imperceptible perturbations to a test example for defrauding DNNs. The… read more here.
Keywords: detecting adversarial; adversarial examples; adversarial example; examples feature ... See more keywords