Enhancing the Privacy of Predictors

The privacy challenge considered here is to prevent an adversary from using available feature values to predict confi- dential information. We propose an algorithm providing such privacy for predictors that have a linear operator in the first stage. Privacy is achieved by zeroing out feature components in the approximate null space of the linear operator. We show that this has little effect on predicting desired information.

Authors

• Ke Xu Beihang University
• Swair Shah
• Tongyi Cao
• Crystal Maung Department of Computer Science, University of Texas at Dallas, Texas, USA
• Haim Schweitzer Department of Computer Science, University of Texas at Dallas, Texas, USA

Keywords

No keywords are indexed for this paper.