yuxiangw / autodp

autodp: A flexible and easy-to-use package for differential privacy

yuxiangw/autodp Issues

An issue when I installed "autodp": Preparing metadata (setup.py) ... error
Updated 2 months ago2
the noise is much greater than the probability. How should I use it correctly?
Updated 5 months ago
Does autodp support arbitrary group size?
Updated 7 months ago2
Update Installation Instructions
Updated 9 months ago3
`bounds` cannot be used together with `method=Brent` in latest version of scipy (>= v1.10.1)
Updated a year ago4
Composing different mechanism with different sensitivies
Closed a year ago5
AFA of composition of subsampled Laplace Mechanism breaks down
Updated a year ago1
Looseness in analytic Gaussian mechanism?
Updated a year ago3
Can't install in GBK locale
Updated a year ago1
Can PATE be used in knowledge distillation to calculate privacy budgets?
Updated a year ago
About the bisection method used for converting RDP to approximate DP
Updated 2 years ago1
Amplification with sampling without replacments is throwing following error.
Closed 2 years ago4
Issue with SSP_scale and AdaSSP_scale inheritance
Closed 3 years ago2
Slow privacy calibration
Closed 3 years ago
Pure Fdp gaussian mechanism doesn't work under composition of multiple rounds
Updated 3 years ago1
documentation question
Closed 3 years ago2
issue with "privacy_calibrator.subsample_epsdelta_inverse(eps,delta,prob=gamma)"
Closed 3 years ago1
huge fan of this work
Updated 4 years ago
difference between eps using this method and abadi
Updated 5 years ago3