Ensuring Privacy in AI Model Fairness Assessment

Exploring a method developed with Oasis Labs, this chapter explains how Instagram users can participate in a survey to contribute sensitive information like gender and race without compromising privacy. Privacy technologies like secure multi-party computation, homomorphic encryption, and differential privacy are utilized to safeguard user data in AI model fairness assessment.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.