Insights      Technology      Applied AI      Episode 83: Understanding Differential Privacy with Chang Liu

Episode 83: Understanding Differential Privacy with Chang Liu

Differential privacy is a technology that’s quickly moving from academia into business. And it’s not just the big companies that are using it. With the intersection of trust and AI a hot topic right now, differential privacy is well on its way to becoming an integral part of the conversation. In this episode, Jon Prial welcomes Chang Liu to the show. Chang is an Applied Research Scientist at Georgian and an expert on differential privacy. In the episode, they talk about what differential privacy is, why it’s important, and why every company needs to think about having it as part of its product and technical strategy.

You’ll hear about:

  • The limits of data anonymization
  • What differential privacy is and why it’s so important
  • Ways to protect your data and be differentially private
  • What epsilon is and what its role is
  • Differential privacy’s potential to solve the cold-start problem
  • Implications for trust

Who Is Chang Liu?

Chang Liu is an Applied Research Scientist and a member of the Georgian Impact team. She brings her in-depth knowledge of mathematical and combinatorial optimization to helping Georgian’s portfolio companies. Prior to joining Georgian, Chang was a Risk Analyst at Manulife Bank, where she built models to assess the bank’s risk exposure based on extensive market research, including evaluating and predicting the impact of the oil price drop to the mortgage lending risks in Alberta in 2014. In that role, she also provided insightful analytics from consumer and credit reports to find optimal lending policies. Prior to this, she worked at a variety of financial institutions, where she designed financial instruments structures for the Standardized Enterprise Database, and supported a fixed income trading business by ensuring accuracy in trade valuation and reporting.

Mentioned in the Podcast

Read more like this

Testing LLMs for trust and safety

We all get a few chuckles when autocorrect gets something wrong, but…

How AI is redefining coding

Sometimes it’s hard to know where to start when it comes to…