Great Models with Great Privacy: Optimizing ML and AI Over Sensitive Data - Databricks

Great Models with Great Privacy: Optimizing ML and AI Over Sensitive Data

Download Slides

There is a growing feeling that privacy concerns dampen innovation in machine learning and AI applied to personal and/or sensitive data. After all, ML and AI are hungry for rich, detailed data and sanitizing data to improve privacy typically involves redacting or fuzzing inputs, which multiple studies have shown can seriously affect model quality and predictive power. While this is technically true for some privacy-safe modeling techniques, it’s not true in general. The root cause of the problem is two-fold. First, most data scientists have never learned how to produce great models with great privacy. Second, most companies lack the systems to make privacy-preserving machine learning & AI easy. This talk will challenge the implicit assumption that more privacy means worse predictions. Using practical examples from production environments involving personal and sensitive data, the speakers will introduce a wide range of techniques-from simple hashing to advanced embeddings-for high-accuracy, privacy-safe model development. Key topics include pseudonymous ID generation, semantic scrubbing, structure-preserving data fuzzing, task-specific vs. task-independent sanitization and ensuring downstream privacy in multi-party collaborations. In addition, we will dig into embeddings as a unique deep learning-based approach for privacy-preserving modeling over unstructured data. Special attention will be given to Spark-based production environments.



« back
About Sim Simeonov

Sim Simeonov is an entrepreneur, investor and startup mentor. He is the founding CTO of Swoop and IPM.ai, startups that use privacy-preserving AI to improve patient outcomes and marketing effectiveness in life sciences and healthcare. Previously, Sim was the founding CTO of Evidon (CrownPeak) & Thing Labs (AOL) and a founding investor in Veracode (Broadcom). In his VC days, Sim was an EIR at General Catalyst Partners and technology partner at Polaris Partners where he helped start five companies the firms invested in, three of which have already been acquired. Before his days as an investor, Sim was vice president of emerging technologies and chief architect at Macromedia (now Adobe). Earlier, he was a founding member and chief architect at Allaire, one of the first Internet platform companies whose flagship product, ColdFusion, ran thousands of sites such as Priceline and MySpace.

About Slater Victoroff

Slater Victoroff is the Founder and CTO of indico data solutions, an Enterprise AI solution for unstructured content with an emphasis on text and NLP. He has been building machine learning solutions for startups, governments, and Fortune 100 companies for the past 5 years and is a frequent speaker at AI conferences.