2000 character limit reached
A Note On Interpreting Canary Exposure (2306.00133v2)
Published 31 May 2023 in cs.CR and cs.LG
Abstract: Canary exposure, introduced in Carlini et al. is frequently used to empirically evaluate, or audit, the privacy of machine learning model training. The goal of this note is to provide some intuition on how to interpret canary exposure, including by relating it to membership inference attacks and differential privacy.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.