Back to Blog

ODSC Recap: Federated SQL and Split Learning 101

  • LiveRamp
  • 2 min read

We had a wonderful time at ODSC West 2021, sharing ideas with the data scientist community on privacy-enhancing technologies. Here are the sessions we presented:

Federated SQL with LiveRamp Safe Haven

Businesses and organizations across sectors are increasingly looking to data partnerships to improve business outcomes. This demonstration of forthcoming LiveRamp Safe Haven capabilities shows how seamless collaboration between trusted parties is made possible by leveraging Federated SQL. 

Greg Gawron, one of our senior staff engineers, shares how these capabilities can be used by companies such as retailers and their suppliers to work collaboratively toward common goals.

Privacy-Preserving Machine Learning: Split Learning and Privacy Attacks

Legitimate privacy concerns often prevent us from making use of distributed data stored in protected silos. How can we enable practitioners to perform advanced analytics on this sensitive (siloed) data whilst safeguarding and not compromising the original data points? 

Watch our tech talk presented by Greg learn more about one of the potential solutions—split learning, a new method for training a modular deep neural network where each module lives in a data silo while upholding quantifiable standards for privacy and security. Greg also dives into the privacy implications of training and releasing the model, including common privacy attacks and general use cases for federated analytics.

To learn more about privacy-enhancing technologies and their role in enabling safe, secure data collaboration, join us on December 14 for a webinar titled, Architecting the Future of Cross-Cloud Data Collaboration. Register here.