Margarita
Vald

Privacy-Preserving Decision Tree Training and Prediction

Intuit

Margarita Vald

Margarita
Vald

Privacy-Preserving Decision Tree Training and Prediction

Intuit

Margarita Vald

Bio

Margarita is a security researcher at Intuit and a Ph.D. student at Tel-Aviv University in the School of Computer Science.


She has a broad interest in secure computation, with privacy-preserving machine-learning being her main research area.
Previously, she was a research fellow at Boston University hosted by Prof. Ran Canetti.

Bio

Margarita is a security researcher at Intuit and a Ph.D. student at Tel-Aviv University in the School of Computer Science.


She has a broad interest in secure computation, with privacy-preserving machine-learning being her main research area.
Previously, she was a research fellow at Boston University hosted by Prof. Ran Canetti.

Abstract

Recent history has shown that the benefits brought forth by today’s data driven culture come at a cost, for example the Yahoo and Equifax data leakages. Such breaches have a devastating impact on individuals and industry, and lead the community to seek for privacy preserving solutions. We discuss one potential approach, which enables machine learning over encrypted data, and thus providing resiliency against information leakage.

 

Several machine learning algorithms have already been adapted to work over encrypted data, including a solution developed at Intuit for training and evaluating decision trees with strong privacy guarantees. We discuss open problems that need to be addressed by the industry for successful adaption of this approach.

Abstract

Recent history has shown that the benefits brought forth by today’s data driven culture come at a cost, for example the Yahoo and Equifax data leakages. Such breaches have a devastating impact on individuals and industry, and lead the community to seek for privacy preserving solutions. We discuss one potential approach, which enables machine learning over encrypted data, and thus providing resiliency against information leakage.

 

Several machine learning algorithms have already been adapted to work over encrypted data, including a solution developed at Intuit for training and evaluating decision trees with strong privacy guarantees. We discuss open problems that need to be addressed by the industry for successful adaption of this approach.

Planned Agenda

Planned Agenda