[Busec] BU Theory Seminar on Auctioning Privacy

Sharon Goldberg goldbe at cs.bu.edu
Sun May 1 23:30:34 EDT 2011


 Hi all

On Friday, Aaron Roth, who will be a professor at UPenn and is currently at
MSR New England, will be speaking at the theory seminar on auctioning
privacy. Aaron has had some seminal results in differential privacy and
learning.

Talk at 3PM in MCS135. Let Steve know if you'd like to meet Aaron. See you
there,

Sharon, on iPhone.

Begin forwarded message:

 *From:* Aaron Roth <aaroth at cis.upenn.edu>
*Date:* May 1, 2011 10:41:04 PM EDT
*To:* Steve Homer <homer at cs.bu.edu>
*Cc:* Sharon Goldberg <goldbe at cs.bu.edu>
*Subject:* *Re: BU Friday theory seminar*

 Hi Steve,

Here are a title and abstract for my talk.

Title: Selling Privacy at Auction
Abstract:
In this talk, we will consider the problem of setting up markets for
private data, though the lens of differential privacy.  Specifically,
we consider a setting in which a data analyst wishes to buy
information from a population from which he can estimate some
statistic. The analyst wishes to obtain an accurate estimate cheaply.
On the other hand, the owners of the private data experience some cost
for their loss of privacy, and must be compensated for this loss.
Agents are selfish, and wish to maximize their profit, so our goal is
to design truthful mechanisms.

Our main result is that such auctions can naturally be viewed and
optimally solved as variants of multi-unit procurement auctions. Based
on this result, we derive auctions for two natural settings which are
optimal up to small constant factors:

1) In the setting in which the data analyst has a fixed accuracy goal,
we show that an application of the classic Vickrey auction achieves
the analyst's accuracy goal while minimizing his total payment.

2) In the setting in which the data analyst has a fixed budget, we
give a mechanism which maximizes the accuracy of the resulting
estimate while guaranteeing that the resulting sum payments do not
exceed the analysts budget.

In both of these results, we ignore the privacy cost due to possible
correlations between an individuals private data and his valuation for
privacy itself. We then show that no individually rational mechanism
can compensate individuals for the privacy loss incurred due to their
reported valuations for privacy. This is nevertheless an important
issue, and modeling it correctly is one of the many exciting
directions for future work.

This talk is based on joint work with Arpita Ghosh
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://cs-mailman.bu.edu/pipermail/busec/attachments/20110501/1acf1918/attachment.html 


More information about the Busec mailing list