Improving Accuracy-Privacy Tradeoff via Model Reprogramming

Improving Accuracy-Privacy Tradeoff via Model Reprogramming

Explore a 36-minute lecture by Pin-Yu Chen from IBM Research on enhancing the balance between accuracy and privacy in machine learning through model reprogramming techniques. Delve into information-theoretic methods for developing trustworthy AI systems and gain insights into innovative approaches for optimizing the accuracy-privacy tradeoff in modern machine learning applications.