Chuan Guo, Jared S. Frank, Kilian Q. Weinberger. Low Frequency Adversarial Perturbation. CoRR abs/1809.08758 (2018).

Guo et al. propose to augment black-box adversarial attacks with low-frequency noise to obtain low-frequency adversarial examples as shown in Figure 1. To this end, the boundary attack as well as the NES attack are modified to sample from a low-frequency Gaussian distribution instead from Gaussian noise directly. This is achieved through an inverse discrete cosine transform as detailed in the paper.

Figure 1: Example of a low-frequency adversarial example.

Also find this summary on ShortScience.org.
What is your opinion on this article? Let me know your thoughts on Twitter @davidstutz92 or LinkedIn in/davidstutz92.