See also Identity resolution.

It is hard to protect privacy by simply anonymizing data. There are many de-anonymization techniques using Machine learning. How about Social networks?

There was a link prediction challenge and a team won it by deanonymizing the dataset[^1]

Guardian reported that NSA has been collecting the phone records of Verizon customers[^2]

Topics #

• Network alignment
• Degree of anonymity

References #

• De-Anonymizing Social Networks: FAQ

• Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Steganography

  • http://www.nd.edu/~netsci/TALKS/Kleinberg.pdf

• k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY

• De-anonymizing Social Networks
• Unique in the Crowd: The privacy bounds of human mobility
• Community-Enhanced De-anonymization of Online Social Networks
• De-anonymizing scale-free social networks by percolation graph matching
• On Your Social Network De-anonymizablity: Quantification and Large Scale Evaluation with Seed Knowledge

[^1]: http://www.kaggle.com/blog/2011/01/15/how-we-did-it-the-winners-of-the-ijcnn-social-network-challenge/ ; De-anonymizing Social Networks by Arvind Narayanan and Vitaly Shmatikov ; http://33bits.org/2011/03/09/link-prediction-by-de-anonymization-how-we-won-the-kaggle-social-network-challenge/

[^2]: "NSA collecting phone records of millions of Verizon customers daily". Guardian. 5 June 2013. http://www.guardian.co.uk/world/2013/jun/06/nsa-phone-records-verizon-court-order.

Incoming Links #

Related Articles (Article 0) #

• Graph matching
• Link prediction
• Social network

Suggested Pages #

• 0.875 Pathogen transmission
• 0.023 Stability selection
• 0.017 Deep learning
• 0.017 Graph isomorphism problem
• 0.017 One-shot learning
• 0.009 Quoc Le
• 0.009 PathBLAST
• 0.007 GraphLab
• 0.004 Naive Bayes classifier
• 0.003 LargeVis
• More suggestions...