Unrestricted Adversarial Examples

Catherine Olsson
Catherine Olsson
Paul Francis Christiano
Paul Francis Christiano

CoRR, Volume abs/1809.08352, 2018.

Cited by: 39|Bibtex|Views105
EI
Other Links: dblp.uni-trier.de|arxiv.org

Abstract:

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achieve high accuracy ...More

Code:

Data:

Your rating :
0

 

Tags
Comments