Statistical Learning Theory Approach for Data Classification with l-diversity

TL;DR

This paper provides a theoretical foundation showing support vector classifiers trained on anatomized data satisfying l-diversity perform comparably to those trained on original data, supporting privacy-preserving data mining.

Contribution

It introduces a theoretical justification for using anatomized data with l-diversity in support vector classification, demonstrating comparable performance to original data.

Findings

Support vector classifiers on anatomized data match original data performance.

Outperforms k-anonymity protected data in classification accuracy.

Validated on multiple public datasets.

Abstract

Corporations are retaining ever-larger corpuses of personal data; the frequency or breaches and corresponding privacy impact have been rising accordingly. One way to mitigate this risk is through use of anonymized data, limiting the exposure of individual data to only where it is absolutely needed. This would seem particularly appropriate for data mining, where the goal is generalizable knowledge rather than data on specific individuals. In practice, corporate data miners often insist on original data, for fear that they might "miss something" with anonymized or differentially private approaches. This paper provides a theoretical justification for the use of anonymized data. Specifically, we show that a support vector classifier trained on anatomized data satisfying l-diversity should be expected to do as well as on the original data. Anatomy preserves all data values, but introduces uncertainty in the mapping between identifying and sensitive values, thus satisfying l-diversity. The theoretical effectiveness of the proposed approach is validated using several publicly available datasets, showing that we outperform the state of the art for support vector classification using training data protected by k-anonymity, and are comparable to learning on the original data.