Adversarial Examples from Cryptographic Pseudo-Random Generators
Abstract
In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary classification task for which (i) a robust classifier exists; yet no non-trivial accuracy can be obtained with an efficient algorithm in (ii) the statistical query model. In the present paper we significantly strengthen both (i) and (ii): we now construct a task which admits (i') a maximally robust classifier (that is it can tolerate perturbations of size comparable to the size of the examples themselves); and moreover we prove computational hardness of learning this task under (ii') a standard cryptographic assumption.
Cite
@article{arxiv.1811.06418,
title = {Adversarial Examples from Cryptographic Pseudo-Random Generators},
author = {Sébastien Bubeck and Yin Tat Lee and Eric Price and Ilya Razenshteyn},
journal= {arXiv preprint arXiv:1811.06418},
year = {2018}
}
Comments
4 pages, no figures