A mutual-information framework trains representations that are simultaneously robust to adversarial examples and private-attribute inference, with new trade-off and leakage bounds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Robust and Privacy-Preserving Representations via Information Theory
A mutual-information framework trains representations that are simultaneously robust to adversarial examples and private-attribute inference, with new trade-off and leakage bounds.