A Mask-Based Adversarial Defense Scheme. (arXiv:2204.11837v1 [cs.LG])

Adversarial attacks hamper the functionality and accuracy of Deep Neural
Networks (DNNs) by meddling with subtle perturbations to their inputs.In this
work, we propose a new Mask-based Adversarial Defense scheme (MAD) for DNNs to
mitigate the negative effect from adversarial attacks. To be precise, our
method promotes the robustness of a DNN by randomly masking a portion of
potential adversarial images, and as a result, the %classification result
output of the DNN becomes more tolerant to minor input perturbations. Compared …

adversarial defense lg