<!doctype html public "-//W3C//DTD W3 HTML//EN">
<html><head><style type="text/css"><!--
blockquote, dl, ul, ol, li { padding-top: 0 ; padding-bottom: 0 }
--></style><title>Re: [e2e] was double blind, now reproduceable
results</title></head><body>
<div>With respect to anonymizing and releasing data, let me recommend
to you a few pages of a CSTB report, "Information Technology
Research for Federal Statistics", National Academy Press, 2000.
See<font face="Lucida Grande" size="-3" color="#000000">
http://www7.nationalacademies.org/cstb/pub_federalstatistics.html</font
>. The focus in that report was to a large extent on data about
people, so privacy was often considered paramount, but I believe the
techniques and state of technology with respect to statistics are
applicable here as well. I recommend to you pp. 34 - 40, the
section titled "Limiting Disclosure" in Chapter 2,
"Research Opportunities". The conclusion to draw from
their examples is that at least in the domains over which they were
looking, it is not well understood how to truly hide the information
one wants to hide. Rather than possibly misrepresenting the
story to you, I recommend you read it for yourselves.</div>
<div><br></div>
<div><x-tab>
</x-tab><x-tab>
</x-tab><x-tab>
</x-tab>Karen</div>
<div><br></div>
<div>At 10:21 AM -0700 5/26/04, Joe Touch wrote:</div>
<blockquote type="cite" cite>RJ Atkinson wrote:<br>
<blockquote type="cite" cite><br>
On May 26, 2004, at 11:52, Joe Touch wrote:<br>
<blockquote type="cite" cite>Impossible is the case I was referring
to. Certainly IF transforms are<br>
possible then they should be used and the data made available.
However,<br>
some data sources aren't comfortable with these transforms, since
there<br>
may be data correlation that ends up compromising the transform.<br>
<br>
Notably those that correlate data to existing Internet routing tables
-<br>
if you found something that preserved not only prefixes but also
the<br>
aggregation, and published it, you'd have to publish the routing
tables<br>
similarly transformed. However, since the untransformed routing
tables<br>
are available publicly anyway, you've compromised your
transform.</blockquote>
</blockquote>
<blockquote type="cite" cite><br>
Whether the transform is compromised would depend
greatly on which<br>
particular routing tables one was working with.</blockquote>
</blockquote>
<blockquote type="cite" cite><br>
Yes. Bob was saying that there exists. I'm claiming there are cases
where there does not exist - i.e., not for all.<br>
<br>
The issue is what to do with a paper published in the case I'm
considering; we all know what to do when you CAN safely anonymize.<br>
<br>
However, note that you don't always know when it's safe - just because
_you_ can't correlate the info doesn't mean someone else can't.<br>
<br>
Joe<br>
<br>
</blockquote>
<blockquote type="cite" cite><br>
Content-Type: application/pgp-signature;
name="signature.asc"<br>
Content-Description: OpenPGP digital signature<br>
Content-Disposition: attachment;
filename="signature.asc"<br>
<br>
Attachment converted: Macintosh HD:signature.asc (
/ ) (0011E338)</blockquote>
<div><br></div>
<div><br></div>
<x-sigsep><pre>--
</pre></x-sigsep>
<div>Karen R. Sollins, Ph.D.<br>
Principal Research Scientist<br>
MIT CSAIL, The Stata Center<br>
32 Vassar St., 32-G818<br>
Cambridge, MA 02139, USA<br>
V: +1 617 253 6006<br>
F: +1 617 253 2673<br>
E: sollins@csail.mit.edu</div>
</body>
</html>