English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Whitening Black-Box Neural Networks

Oh, S. J., Augustin, M., Schiele, B., & Fritz, M. (2017). Whitening Black-Box Neural Networks. Retrieved from http://arxiv.org/abs/1711.01768.

Item is

Files

show Files
hide Files
:
arXiv:1711.01768.pdf (Preprint), 2MB
Name:
arXiv:1711.01768.pdf
Description:
File downloaded from arXiv at 2018-02-01 09:49
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Oh, Seong Joon1, Author              
Augustin, Max1, Author              
Schiele, Bernt1, Author              
Fritz, Mario1, Author              
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Statistics, Machine Learning, stat.ML,Computer Science, Cryptography and Security, cs.CR,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
 Abstract: Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary information or make the system more vulnerable. This work shows that such attributes of neural networks can be exposed from a sequence of queries. This has multiple implications. On the one hand, our work exposes the vulnerability of black-box neural networks to different types of attacks -- we show that the revealed internal information helps generate more effective adversarial examples against the black box model. On the other hand, this technique can be used for better protection of private content from automatic recognition models using adversarial examples. Our paper suggests that it is actually hard to draw a line between white box and black box models.

Details

show
hide
Language(s): eng - English
 Dates: 2017-11-062017
 Publication Status: Published online
 Pages: 12 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1711.01768
URI: http://arxiv.org/abs/1711.01768
BibTex Citekey: Oh1711.01768
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show