Conference item icon

Conference item

A statistical approach to assessing neural network robustness

Abstract:

We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate the probability of the event that the property is violated under an input model. Our approach critically varies from the formal verification framework in that when the property can be violated, it provides an informative notion of how robust the network is, rather than just the conventional assertion that the network ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Statistics
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Statistics
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Lady Margaret Hall
Role:
Author
Publisher:
International Conferences on Learning Representations Publisher's website
Publication date:
2019-02-21
Acceptance date:
2018-12-20
Pubs id:
pubs:956243
URN:
uri:953c3599-4cef-4a8a-a2a8-546877ea5597
UUID:
uuid:953c3599-4cef-4a8a-a2a8-546877ea5597
Local pid:
pubs:956243

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP