
⟳ Felipe Gomez retweeted
A Gaussian mechanism with ε = 6 can be less private than one with ε = 8. This points to a problem with how we report privacy guarantees in machine learning. A thread 🧵

Harvard grad student and @doecsgf fellow. Interested in differential privacy and fairness

A Gaussian mechanism with ε = 6 can be less private than one with ε = 8. This points to a problem with how we report privacy guarantees in machine learning. A thread 🧵