Netflix paper home
This page is intended to be a collection of links about the Netflix paper. Note that I’m calling it the “Netflix” paper only for memorability; as we explain in the paper and in the FAQ, the consequences of our techniques go far beyond that dataset. Indeed, that is the reason this website was started.
Abstract
We present a new class of statistical de-anonymization attacks against high-dimensional micro-data, such as individual preferences, recommendations, transaction records and so on. Our techniques are robust to perturbation in the data and tolerate some mistakes in the adversary’s background knowledge.
We apply our de-anonymization methodology to the Netflix Prize dataset, which contains anonymous movie ratings of 500,000 subscribers of Netflix, the world’s largest online movie rental service. We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily identify this subscriber’s record in the dataset. Using the Internet Movie Database as the source of background knowledge, we successfully identified the Netflix records of known users, uncovering their apparent political preferences and other potentially sensitive information.
Links
- Abridged version appeared at Oakland ’08. (pdf, slides)
- Full version: CoRR tech report
- FAQ
- Recent press: PET Award
From 2007: Wired, Slashdot, SecurityFocus
From 2006: New Scientist, Wired - Netflix: the back story. (Sort of an extended Acknowledgments section for the paper.)
- Posts tagged Netflix on this blog.
1. Law review article about Netflix paper « 33 Bits of Entropy | September 30, 2008 at 9:47 pm
[…] 30, 2008 David Molnar pointed me to an article about the Netflix dataset de-anonymization paper in the Shidler Journal of Law. I’m very happy to see this; when we wrote our paper, we were […]
2. Lendingclub.com: A de-anonymization walkthrough « 33 Bits of Entropy | November 12, 2008 at 9:40 pm
[…] love this field, since it is very similar to the high dimensional data in the Netflix paper. Since Lendingclub was launched as a Facebook application, it appears that they are asking for […]
3. De-anonymization is not X: The Need for Re-identification Science « 33 Bits of Entropy | October 14, 2009 at 9:42 pm
[…] noise. Let’s move on to other connections that turned out to be red herrings. Prior to our Netflix paper, Frankowski et al. studied de-anonymization of users via movie ratings collected as part of the […]