Evaluating AI Privacy: A Knowledge Gap
We observe that the ML community cannot sufficiently access privacy tech. People interested in safe ML topics such as model alignment often do not have a clear understanding of cryptography-based techniques when applied to ML.
On the other hand, cryptographers want to apply their knowledge, especially with practical security management, to machine learning systems. Yet they face the problem of a completely different mindset from machine learning researchers who currently drive the development of these systems.
These communities do not engage with each other, partly because they do not have a shared common ground. This tutorial can bridge the gap between cryptography and effective decentralized ML training and evaluation.
Join us at NeurIPS 2024 for a tutorial on Privacy ML: Meaningful-Privacy Preserving Machine Learning and How to Evaluate AI Privacy.