
Make the model yours
Customizability is the most underrated idea in AI right now. Runpod CEO Zhen Lu on why a model tuned on your data beats a bigger one on the job you actually have.
Blog
Runpod now offers encrypted volumes to help secure sensitive data stored in persistent volumes. This post outlines the benefits and tradeoffs of volume.

At Runpod, we're always looking to offer more value to our clients. One of the things we take seriously is security. To this end, we have implemented the ability to encrypt your persistent volumes.
Runpod now offers encrypted volumes! This means that you have the option to choose your level of data security!
There are several benefits to using encrypted volumes:
There are also some drawbacks to using encrypted volumes:
You can enable volume encryption by checking the "Encrypt Volume" checkbox during deploy.

Note that you can only do this during the deploy step. You cannot change encryption options after the pod is already deployed. We will handle the encryption keys for you if you deploy through the web platform. If you would prefer to choose your own encryption key, you can deploy using the API.
If you have sensitive data that you need to protect, we recommend using encrypted volumes. However, if you do not have sensitive data or if you are unwilling to trade performance for security, we recommend using non-encrypted volumes.
If you have any questions about encrypted volumes or any other features of Runpod, please contact us through Discord, chat, or email. We would be happy to help!
Author profile: Zhen Lu
Blog Posts

Customizability is the most underrated idea in AI right now. Runpod CEO Zhen Lu on why a model tuned on your data beats a bigger one on the job you actually have.

A practical guide to expanding multi-node GPU workloads in place.
.avif)
A hands-on tutorial for wiring GPU-backed tools into an MCP server, and hosting the compute on Runpod Serverless.