A mutual-information-based criterion, Dmia, predicts model inversion attack difficulty in collaborative inference, and the SiftFunnel defense suppresses the criterion's factors to raise reconstruction error with only about a 3% accuracy drop.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference
A mutual-information-based criterion, Dmia, predicts model inversion attack difficulty in collaborative inference, and the SiftFunnel defense suppresses the criterion's factors to raise reconstruction error with only about a 3% accuracy drop.