Differential Privacy: We provide an experimental implementation of DP-SGD that modifies the optimizer to offer provable guarantees of privacy, enabling safe training on private data. Differential Privacy can cause a hit to utility, often requiring larger datasets to work well, but it uniquely provides privacy guarantees against both known and unknown attacks on data. Differential Privacy can be enabled by setting dp: True
and can be modified using the associated configuration settings: dp_noise_multiplier
, dp_l2_norm_clip
and dp_microbatches
. These settings can be used to adjust the privacy vs accuracy balance of the synthetic dataset.