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.
Improving Accuracy-Privacy Tradeoff via Model Reprogramming
Overview
Syllabus
Improving Accuracy-Privacy Tradeoff via Model Reprogramming
Taught by
Simons Institute
Related Courses
-
Privacy and Fairness in Collaborative AI
-
Contraction of Markov Kernels and Differential Privacy - Part I
-
Differential Privacy & Variants
-
The Saddle-Point Accountant for Differential Privacy
-
Fundamental Trade-Offs in FL-FA - Sparsity - DP - Communication Constraints
-
Guarding the ML Galaxy - Beyond Accuracy to Privacy and Security
