Persistent Betti-1 of smashed activations is proposed as an attack-free indicator of feature-inversion risk in split learning, used for split selection and regularization.
Ppsfl: Privacy-preserving split federated learning for heterogeneous data in edge-based internet of things.Future Generation Computer Systems, 156:231–241, 2024
1 Pith paper cite this work, alongside 29 external citations. Polarity classification is still indexing.
1
Pith paper citing it
29
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage
Persistent Betti-1 of smashed activations is proposed as an attack-free indicator of feature-inversion risk in split learning, used for split selection and regularization.