The paper introduces privacy tokens, learned gradient embeddings, to estimate mutual information between training data and gradients for real-time privacy risk monitoring during model training.
Mem- bership inference attacks against machine learning mod- els
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
The paper introduces privacy tokens, learned gradient embeddings, to estimate mutual information between training data and gradients for real-time privacy risk monitoring during model training.