On the Geometry of Adversarial Examples On the Geometry of Adversarial Examples
Paper summary Khoury and Hadfield-Menell provide two important theoretical insights regarding adversarial robustness: it is impossible to be robust in terms of all norms, and adversarial training is sample inefficient. Specifically, they study robustness in relation to the problem’s codimension, i.e., the difference between the dimensionality of the embedding space (e.g., image space) and the dimensionality of the manifold (where the data is assumed to actually live on). Then, adversarial training is shown to be sample inefficient in high codimensions. Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
On the Geometry of Adversarial Examples
Khoury, Marc and Hadfield-Menell, Dylan
arXiv e-Print archive - 2018 via Local Bibsonomy
Keywords: dblp

Summary by David Stutz 1 year ago
Your comment:

ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and