Protegrity Synthetic Data on

Introduction

Mon, 01 Jan 0001 00:00:00 +0000

This section explains why organizations use Synthetic Data and how Protegrity Synthetic Data preserves statistical utility while reducing privacy risk.

Organizations need realistic datasets for model training, testing, and cross-team collaboration without exposing sensitive information. Traditional methods such as masking and redaction can reduce data utility for analytics and machine learning.

Protegrity Synthetic Data learns patterns and distributions from source data. It then generates new records that reflect these patterns without reproducing the original personal records.

Understanding the Architecture and Components

Mon, 01 Jan 0001 00:00:00 +0000

Protegrity Synthetic Data generates realistic, privacy-safe synthetic datasets using machine learning models. It learns patterns and distributions from real data, then produces new records with similar statistical properties.

Protegrity Synthetic Data uses Kubernetes for scalable Synthetic Data generation and supports deployment on AWS EKS.

Component Diagram

The following diagram shows the deployment architecture and communication between components.

graph TD
 User([User / Client Application]) -->|HTTPS :443| GW[PPC Gateway]
 User --> SDK[Synthetic Data Python SDK]
 SDK -->|HTTPS :443| GW

 GW -->|:8000 /pty/syntheticdata/v2| App[Synthetic Data
REST Server + ML Engine]

 App -->|:5432 jobstatedb + mlopsdb| DB[(PostgreSQL)]

 subgraph EKS [EKS Cluster · synthetic-data-ns]
 GW
 App
 DB
 end

 subgraph AWS
 S3[(S3 Bucket
Data Storage)]
 IAM[IAM Role
Pod Identity]
 end

 App -.->|assumes| IAM
 IAM -.->|grants access| S3
 App <-->|read / write| S3

Communication Ports

Port	Direction	Description
443	User and SDK → PPC Gateway	HTTPS entry point for user and SDK traffic
8000	Gateway → Synthetic Data REST Server	Synthetic Data REST API (`/pty/syntheticdata/v2`)
5432	Synthetic Data REST Server → PostgreSQL	Internal connection for job state (`jobstatedb`) and MLOps model tracking (`mlopsdb`)

Components

PPC Gateway: Exposes the external HTTPS endpoint and routes requests to the Synthetic Data REST API.

Prerequisites for Deployment

Mon, 01 Jan 0001 00:00:00 +0000

For more information about the tools and permissions required for deployment, refer to Prerequisites.

Server Installation

Mon, 01 Jan 0001 00:00:00 +0000

For more information about installation steps, refer to Installation.

User Creation in PPC

Mon, 01 Jan 0001 00:00:00 +0000

For more information about creating user in PPC, refer to Configuring Protegrity Synthetic Data.

Uninstallation and Cleanup

Mon, 01 Jan 0001 00:00:00 +0000

For more information about removing the Synthetic Data service and all associated Kubernetes and AWS resources, refer to Uninstallation and Cleanup.

Troubleshooting

Mon, 01 Jan 0001 00:00:00 +0000

Diagnostic Flowchart

Use the following flowchart to identify the cause of common issues.

flowchart TD
 Start[Problem?] --> ServerRunning{Server pods Running?}
 ServerRunning -->|No| PodIssue[Check pod logs<br/>kubectl logs -n synthetic-data-ns]
 ServerRunning -->|Yes| APIWorks{Does API respond?}
 APIWorks -->|No| NetworkIssue[Check Service and Gateway<br/>kubectl get svc -n synthetic-data-ns]
 APIWorks -->|Yes| ValidationFails{Request fails?}
 ValidationFails -->|Yes| ConfigIssue[Review request config<br/>Check model and data parameters]
 ValidationFails -->|No| OtherIssue[Check logs or open a support ticket]
 style Start fill:#e1f5ff

Common Issues

Pods not reach the `Running` state

kubectl describe pod -n synthetic-data-ns <POD_NAME>
kubectl logs -n synthetic-data-ns <POD_NAME>

Check that the Karpenter NodePool provisioned the required nodes. Ensure that OpenTofu created the S3 bucket and IAM role.

Protegrity Synthetic Data on

Introduction

Understanding the Architecture and Components

Component Diagram

Communication Ports

Components

Prerequisites for Deployment

Server Installation

User Creation in PPC

Uninstallation and Cleanup

Troubleshooting

Diagnostic Flowchart

Common Issues

Pods not reach the Running state

Pods not reach the `Running` state