A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Stronger and Faster Wasserstein Adversarial Attacks
[article]
2020
arXiv
pre-print
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to "small, imperceptible" perturbations known as adversarial attacks. While the majority of existing attacks focus on measuring perturbations under the ℓ_p metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring image quality and has recently risen as a compelling alternative to the ℓ_p metric in adversarial attacks. However,
arXiv:2008.02883v1
fatcat:xeu7cw3ctrfopit2dgw662gqe4