Enhancing the Privacy of Predictors
DOI:
https://doi.org/10.1609/aaai.v31i1.11087Keywords:
Privacy, Multi-label Learning, Linear RegressionAbstract
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.
Downloads
Published
2017-02-12
How to Cite
Xu, K., Shah, S., Cao, T., Maung, C., & Schweitzer, H. (2017). Enhancing the Privacy of Predictors. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11087
Issue
Section
Student Abstract Track