Fine-tune Gretel's privacy protection filters to prevent adversarial attacks and better meet your data sharing needs.
In addition to the privacy inherent in the use of synthetic data, we can add supplemental protection by means of Gretel's privacy filters. These file configuration settings help to ensure that the generated data is safe from adversarial attacks.
There are four privacy protection mechanisms:
Overfitting Prevention: This mechanism ensures that the synthetic model will stop training before it has a chance to overfit. When a model is overfit, it will start to memorize the training data as opposed to learning generalized patterns in the data. This is a severe privacy risk as overfit models are commonly exploited by adversaries seeking to gain insights into the original data. Overfitting prevention is enabled using the
Similarity Filters: Similarity filters ensure that no synthetic record is overly similar to a training record. Overly similar training records can be a severe privacy risk as adversarial attacks commonly exploit such records to gain insights into the original data. Similarity Filtering is enabled by the
Outlier Filters: Outlier filters ensure that no synthetic record is an outlier with respect to the training dataset. Outliers revealed in the synthetic dataset can be exploited by Membership Inference Attacks, Attribute Inference, and a wide variety of other adversarial attacks. They are a serious privacy risk. Outlier Filtering is enabled by the
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: Trueand can be modified using the associated configuration settings:
dp_microbatches. These settings can be used to adjust the privacy vs accuracy balance of the synthetic dataset.
Synthetic model training and generation are driven by a configuration file. Here is an example configuration with commonly used privacy settings.
The Privacy Protection Level (PPL) is calculated based on the enabled privacy mechanisms and displayed in the Gretel Performance Report. The top of the report displays a gauge showing the score for the generated synthetic data.
Privacy Protection Level in the Gretel Synthetic Report
Values can range from Excellent to Poor, and we provide a matrix with the recommended Privacy Protection Levels for a given data sharing use case.
We also provide a summary of available and enabled privacy protections.
Privacy Settings At A Glance