Conference item icon

Conference item

With friends like these, who needs adversaries?

Abstract:

The vulnerability of deep image classification networks to adversarial attack is now well known, but less well understood. Via a novel experimental analysis, we illustrate some facts about deep convolutional networks for image classification that shed new light on their behaviour and how it connects to the problem of adversaries. In short, the celebrated performance of these networks and their vulnerability to adversarial attack are simply two sides of the same coin: the input image-space dir...

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:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
Publisher:
Neural Information Processing Systems Proceedings Publisher's website
Publication date:
2018-12-20
Acceptance date:
2018-09-05
Pubs id:
pubs:953446
URN:
uri:bbc48c6f-d259-40a5-967a-106978f3d1d9
UUID:
uuid:bbc48c6f-d259-40a5-967a-106978f3d1d9
Local pid:
pubs:953446

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