SafeSplit detects poisoned client updates in U-shaped split learning by comparing DCT frequency distances and rotational distances of backbone states, then rolling back to the latest benign checkpoint; experiments show backdoor accuracy below 5% across five image datasets.
https://www.govinfo.gov/content/pkg/PLAW-104publ191/pdf/ PLAW-104publ191.pdf
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
SafeSplit detects poisoned client updates in U-shaped split learning by comparing DCT frequency distances and rotational distances of backbone states, then rolling back to the latest benign checkpoint; experiments show backdoor accuracy below 5% across five image datasets.