English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Image Manipulation against Learned Models Privacy and Security Implications

Oh, S. J. (2018). Image Manipulation against Learned Models Privacy and Security Implications. PhD Thesis, Universität des Saarlandes, Saarbrücken. doi:10.22028/D291-27304.

Item is

Files

show Files
hide Files
:
thesisSeong.pdf (Any fulltext), 54MB
 
File Permalink:
-
Name:
thesisSeong.pdf
Description:
-
OA-Status:
Visibility:
Restricted (Max Planck Institute for Informatics, MSIN; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show
hide
Locator:
http://dx.doi.org/10.22028/D291-27304 (Any fulltext)
Description:
-
OA-Status:
Green

Creators

show
hide
 Creators:
Oh, Seong Joon1, 2, Author           
Schiele, Bernt1, Advisor           
Fritz, Mario1, Referee           
Shmatikov, Vitaly3, Referee
Belongie, Serge3, Referee
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2International Max Planck Research School, MPI for Informatics, Max Planck Society, Campus E1 4, 66123 Saarbrücken, DE, ou_1116551              
3External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Machine learning is transforming the world. Its application areas span privacy
sensitive and security critical tasks such as human identification and self-driving
cars. These applications raise privacy and security related questions that are not
fully understood or answered yet: Can automatic person recognisers identify people
in photos even when their faces are blurred? How easy is it to find an adversarial
input for a self-driving car that makes it drive off the road?
This thesis contributes one of the first steps towards a better understanding of
such concerns. We observe that many privacy and security critical scenarios for
learned models involve input data manipulation: users obfuscate their identity by
blurring their faces and adversaries inject imperceptible perturbations to the input
signal. We introduce a data manipulator framework as a tool for collectively describing
and analysing privacy and security relevant scenarios involving learned models.
A data manipulator introduces a shift in data distribution for achieving privacy or
security related goals, and feeds the transformed input to the target model. This
framework provides a common perspective on the studies presented in the thesis.
We begin the studies from the user’s privacy point of view. We analyse the
efficacy of common obfuscation methods like face blurring, and show that they
are surprisingly ineffective against state of the art person recognition systems. We
then propose alternatives based on head inpainting and adversarial examples. By
studying the user privacy, we also study the dual problem: model security. In model
security perspective, a model ought to be robust and reliable against small amounts
of data manipulation. In both cases, data are manipulated with the goal of changing
the target model prediction. User privacy and model security problems can be
described with the same objective.
We then study the knowledge aspect of the data manipulation problem. The more
one knows about the target model, the more effective manipulations one can craft.
We propose a game theoretic manipulation framework to systematically represent
the knowledge level on the target model and derive privacy and security guarantees.
We then discuss ways to increase knowledge about a black-box model by only querying
it, deriving implications that are relevant to both privacy and security perspectives.

Details

show
hide
Language(s): eng - English
 Dates: 2018-08-062018-08-132018
 Publication Status: Issued
 Pages: 218 p.
 Publishing info: Saarbrücken : Universität des Saarlandes
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Ohphd18
DOI: 10.22028/D291-27304
URN: urn:nbn:de:bsz:291-scidok-ds-273042
Other: hdl:20.500.11880/27146
 Degree: PhD

Event

show

Legal Case

show

Project information

show

Source

show