k-anonymity: a model for protecting privacy
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
\ell -Diversity: Privacy Beyond \kappa -Anonymity
ICDE '06 Proceedings of the 22nd International Conference on Data Engineering
Anatomy: simple and effective privacy preservation
VLDB '06 Proceedings of the 32nd international conference on Very large data bases
Revisiting the uniqueness of simple demographics in the US population
Proceedings of the 5th ACM workshop on Privacy in electronic society
Privacy, accuracy, and consistency too: a holistic solution to contingency table release
Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Minimality attack in privacy preserving data publishing
VLDB '07 Proceedings of the 33rd international conference on Very large data bases
The cost of privacy: destruction of data-mining utility in anonymized data publishing
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Composition attacks and auxiliary information in data privacy
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
FOCS '08 Proceedings of the 2008 49th Annual IEEE Symposium on Foundations of Computer Science
Universally utility-maximizing privacy mechanisms
Proceedings of the forty-first annual ACM symposium on Theory of computing
Differentially private recommender systems: building privacy into the net
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Attacks on privacy and deFinetti's theorem
Proceedings of the 2009 ACM SIGMOD International Conference on Management of data
Differential privacy: a survey of results
TAMC'08 Proceedings of the 5th international conference on Theory and applications of models of computation
Proceedings of the forty-second ACM symposium on Theory of computing
Data mining with differential privacy
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Minimizing minimality and maximizing utility: analyzing method-based attacks on anonymized data
Proceedings of the VLDB Endowment
Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
ICALP'06 Proceedings of the 33rd international conference on Automata, Languages and Programming - Volume Part II
Limiting disclosure of sensitive data in sequential releases of databases
Information Sciences: an International Journal
Secure distributed computation of anonymized views of shared databases
ACM Transactions on Database Systems (TODS)
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Publishing microdata with a robust privacy guarantee
Proceedings of the VLDB Endowment
Non-interactive differential privacy: a survey
Proceedings of the First International Workshop on Open Data
A propagation model for provenance views of public/private workflows
Proceedings of the 16th International Conference on Database Theory
Membership privacy: a unifying framework for privacy definitions
Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Hi-index | 0.04 |
Over the last decade great strides have been made in developing techniques to compute functions privately. In particular, Differential Privacy gives strong promises about conclusions that can be drawn about an individual. In contrast, various syntactic methods for providing privacy (criteria such as k-anonymity and l-diversity) have been criticized for still allowing private information of an individual to be inferred. In this paper, we consider the ability of an attacker to use data meeting privacy definitions to build an accurate classifier. We demonstrate that even under Differential Privacy, such classifiers can be used to infer "private" attributes accurately in realistic data. We compare this to similar approaches for inference-based attacks on other forms of anonymized data. We show how the efficacy of all these attacks can be measured on the same scale, based on the probability of successfully inferring a private attribute. We observe that the accuracy of inference of private attributes for differentially private data and $l$-diverse data can be quite similar.