Machine Learning

Evaluating Differentially Private Machine Learning in Practice

What seems safe, might not be safe in practice.

Inference Privacy Risks of Machine Learning Models

Comparing the differential privacy implementations by quantifying their privacy leakage.

Detecting Vague Words and Phrases in Requirements Documents in a Multilingual Environment

We identify vague terms across English, Portuguese and Spanish software requirement documents.

Aggregating Private Sparse Learning Models Using Multi-Party Computation

We use MPC to aggregate models in a private and distributed way.

Privacy Preserving Machine Learning

Combining differential privacy and multi-party computation techniques for private machine learning.