@techreport{TD:101323,
	att_abstract={{Privacy-preserving data publishing is an important problem that has
been the focus of extensive study.
The state-of-the-art goal for this problem is differential privacy,
which offers a strong degree of privacy protection without making
restrictive assumptions about the adversary.
Existing techniques using differential privacy, however, cannot
effectively handle the publication of high-dimensional data.
In particular, when the input dataset contains a large number of
attributes, existing methods require injecting a prohibitive amount of
noise compared to the signal in the data, which renders the
published data next to useless.

To address the deficiency of the existing methods, this paper presents
PrivBayes, a differentially private method for releasing
high-dimensional data.
Given a dataset $D$, PrivBayes first constructs a Bayesian network
$mathcal{N}$, which (i) provides a succinct model of the correlations
among the attributes in $D$ and (ii) allows us to approximate the
distribution of data in $D$ using a set $mathcal{P}$ of
low-dimensional marginals of $D$.
After that, PrivBayes injects noise
into each marginal in $mathcal{P}$ to ensure differential privacy,
and then uses the noisy marginals and the Bayesian network to
construct an approximation of the data distribution in $D$. Finally,
PrivBayes samples tuples from the approximate distribution to
construct a synthetic dataset, and then releases the synthetic
data. Intuitively, PrivBayes circumvents the curse of dimensionality,
as it injects noise into the low-dimensional marginals in
$mathcal{P}$ instead of the high-dimensional dataset $D$.
Private construction of Bayesian networks turns out to be
significantly challenging, and w
e introduce a novel approach that uses
a surrogate function for mutual information to build the model more
accurately. We experimentally evaluate PrivBayes on real data, and demonstrate that it significantly outperforms existing solutions in terms of data utility.}},
	att_authors={cp2838, ds8961},
	att_categories={C_BB.1},
	att_copyright={{ACM}},
	att_copyright_notice={{(c) ACM, 2013. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 2013 {{, 2014-06-22}}.
}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={differential privacy, Bayes networks},
	att_techdoc={true},
	att_techdoc_key={TD:101323},
	att_url={http://web1.research.att.com:81/techdocs_downloads/TD:101323_DS1_2014-06-30T04:52:37.860Z.pdf},
	author={Cecilia Procopiuc and Divesh Srivastava and Graham Cormode and Xiaokui Xiao and Jun Zhang},
	institution={{ACM Sigmod}},
	month={June},
	title={{PrivBayes: Private Data Release via Bayesian Networks}},
	year=2014,
}