Making ML models differentially private: Best practices and open challenges

Large machine learning (ML) models are ubiquitous in modern applications: from spam filters to recommender systems and virtual assistants. These models achieve remarkable performance partially due to the abundance of available training data. However, these data can sometimes contain private information, including personal identifiable information, copyright material, etc. Therefore, protecting the privacy of the training data is critical to practical, applied ML.

Differential Privacy (DP) is one …

alex applications assistants best practices challenges data deep learning engineers filters google google research machine machine learning making ml models modern applications performance practices recommender systems research security and privacy software software engineers spam staff systems training training data virtual virtual assistants