Anonymized
Somebody has sued Netflix, claiming that their release of “anonymized” data as part of the Netflix prize allowed her to be identified. What’s particularly interesting is how it went down:
just weeks after the contest began, two University of Texas researchers — Arvind Narayanan and Vitaly Shmatikov — identified several NetFlix users by comparing their “anonymous” reviews in the Netflix data to ones posted on the Internet Movie Database website. Revelations included identifying their political leanings and sexual orientation.
Putting aside the suit, it’s interesting to think about how anonymous any data can be when their is a plethora of non-anonymous data available for comparison. This is more interesting than the AOL search data because in that case the data itself included the clues. (Here’s a New York Times article about the AOL incident if you want a refresh.) I suspect we will see a lot more cases like this in the future.
Hi, I'm 
this was the very conversation I was having yesterday with a couple of friends, independent of the Netflix event. It’s all based on a model of privacy that considers information to be a series of unique items, rather than a system of interrelated records and meanings.
Never mind any of that, tho, where are you in the world and when do we get together to make things?
Very easy to put data points together and come up with these profiles with pretty good accuracy I suppose. People just share way too much. They don’t care about the the little pieces they spread all over the web let alone the big puzzle it creates.
Hey, you used to write fantastic, but the last few posts have been kinda boring… I miss your great writings. Past several posts are just a little bit out of track! come on!