A Note On Interpreting Canary Exposure
arXiv:2306.00133v26 citations
Originality Synthesis-oriented
AI Analysis
This provides clarification for researchers and practitioners using privacy audits, but it is incremental as it builds on existing concepts without introducing new methods.
The paper tackles the interpretation of canary exposure, a method for evaluating privacy in machine learning training, by relating it to membership inference attacks and differential privacy.
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.