@inproceedings{DBLP:conf/pkdd/LiuGK06,
  author    = {Kun Liu and
               Chris Giannella and
               Hillol Kargupta},
  title     = {An Attacker's View of Distance Preserving Maps for Privacy
               Preserving Data Mining},
  booktitle = {PKDD},
  year      = {2006},
  pages     = {297-308},
  ee        = {http://dx.doi.org/10.1007/11871637_30},
  crossref  = {DBLP:conf/pkdd/2006},
  bibsource = {DBLP, http://dblp.uni-trier.de} }

@proceedings{DBLP:conf/pkdd/2006,
  editor    = {Johannes F{\"u}rnkranz and
               Tobias Scheffer and
               Myra Spiliopoulou},
  title     = {Knowledge Discovery in Databases: PKDD 2006, 10th European
               Conference on Principles and Practice of Knowledge Discovery
               in Databases, Berlin, Germany, September 18-22, 2006, Proceedings},
  booktitle = {PKDD},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {4213},
  year      = {2006},
  isbn      = {3-540-45374-1},
  bibsource = {DBLP, http://dblp.uni-trier.de} }

An Attacker's View of Distance Preserving Maps for Privacy Preserving Data Mining 
Kun Liu, Chris Giannella, Hillol Kargupta 
Book Series Lecture Notes in Computer Science 
Publisher Springer Berlin / Heidelberg 
ISSN 0302-9743 (Print) 1611-3349 (Online) 
Volume Volume 4213/2006 
Book Knowledge Discovery in Databases: PKDD 2006 
DOI 10.1007/11871637 
Copyright 2006 
ISBN 978-3-540-45374-1 
Category Long Papers 
DOI 10.1007/11871637_30 
Pages 297-308 
Subject Collection Computer Science 
SpringerLink Date Thursday, September 21, 2006 

Abstract

We examine the effectiveness of distance preserving transformations in
privacy preserving data mining. These techniques are potentially very
useful in that some important data mining algorithms can be
efficiently applied to the transformed data and produce exactly the
same results as if applied to the original data e.g. distance-based
clustering, k-nearest neighbor classification. However, the issue of
how well the original data is hidden has, to our knowledge, not been
carefully studied. We take a step in this direction by assuming the
role of an attacker armed with two types of prior information
regarding the original data. We examine how well the attacker can
recover the original data from the transformed data and prior
information. Our results offer insight into the vulnerabilities of
distance preserving transformations.