Pure joint output/timing differential privacy is achievable in the unbounded setting with polynomially vanishing error when the input length is known to the RAM program, and that rate is essentially necessary.
Privacy-preserving machine learning with homomorphic encryption
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
-
Securing Unbounded Differential Privacy Against Timing Attacks
Pure joint output/timing differential privacy is achievable in the unbounded setting with polynomially vanishing error when the input length is known to the RAM program, and that rate is essentially necessary.