Privacy-preserving machine learning (PPML) is an emerging field that is in active research. The most prolific successful machine learning models today are built by aggregating all data together at a central location. While centralized techniques are great, there are plenty of scenarios such as user privacy, legal concerns, business competitiveness, or bandwidth limitations, wherein data cannot be aggregated together. Federated Learning can help overcome all these challenges with its decentralized strategy for building machine learning models. Paired with privacy-preserving techniques such as differential privacy and encryptions, Federated Learning presents a promising new way for advancing machine learning solutions.

In this talk, we will be bringing the audience up to speed with the progress in Privacy-preserving machine learning while discussing platforms for developing models and present a demo of healthcare use cases.

Key Takeaways

• Understand the need for PPML Techniques
• Introduction to Federated Learning with an example
• Dwelling deeper to PPML techniques such as Differential Privacy and Homomorphic Encryption
• Quick Demo of our upcoming PPML Platform

If you want to learn more about our Artificial Intelligence & Machine Learning offerings, please reach out to us.