Duet introduces a linear type system that automatically verifies differential privacy for higher-order programs, supporting multiple modern privacy definitions and per-input privacy accounting, demonstrated on machine learning algorithms.
scikit-learn: Standardization, or mean removal and variance scaling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.PL 1years
2019 1verdicts
CONDITIONAL 1roles
method 1polarities
unclear 1representative citing papers
citing papers explorer
-
Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy
Duet introduces a linear type system that automatically verifies differential privacy for higher-order programs, supporting multiple modern privacy definitions and per-input privacy accounting, demonstrated on machine learning algorithms.