top of page
OUR SPEAKERS
Share on:
Margarita is a security researcher at Intuit and holds a Ph.D. in Computer Science from Tel-Aviv University.
She has a broad interest in secure computation, data protection and applied security research. Her main focus is privacy enhancing technologies and provable security, including privacy for blockchains.
Previously, she was a research fellow at Boston University hosted by Prof. Ran Canetti and Google PhD fellow.
Margarita Vald
Principal Cryptography Researcher
English, Hebrew
Languages:
Location:
Tel Aviv, Israel
Can also give an online talk/webinar
Paid only. Contact speaker for pricing!
MY TALKS
Unlocking Data Privacy Challenges in Machine Learning: The Case of Decision Trees
Data / AI / ML, Security / Privacy
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, where the data of 147 million people was publicly exposed. Such breaches have a devastating impact both on individuals and the industry, leading the community to seek privacy-preserving solutions.
In this talk, I will present 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. I will share our solution and discuss open issues that need to be addressed by the industry for successful adoption of this approach.


My talk is based on the following published papers:
* "Privacy-Preserving Decision Trees Training and Prediction" ECML, 2020
* "CSHER: A System for Compact Storage with HE-Retrieval" USENIX, 2023
Unlocking Data Privacy Challenges in Machine Learning: The Case of Decision Trees
Completed
true
Visible
true
Order
5
bottom of page