tensorflow-serving-fips

Fips

Stig

Updated 11 hours ago

TensorFlow Serving FIPS Overview

Secure your stack with a FIPS-validated, hardened TensorFlow Serving image freshly-built by Minimus. Minimus images always include the most up-to-date package version for all packages and dependencies contained in the image.

TensorFlow Serving is used to serve machine learning models in production environments. It handles model loading, versioning, and inference requests with low latency and high throughput, supporting multiple models and versions simultaneously. The system provides a gRPC and REST API interface for client applications to request predictions from deployed models.

FIPS 140-3 Certification

This image is FIPS-validated to ensure its cryptographic operations meet the Federal Information Processing Standards (FIPS) required for secure government and regulated environments. Its core cryptographic modules are validated under the NIST Cryptographic Module Validation Program (CMVP) and comply with the FIPS 140-3 standard.

To verify that the FIPS 140-3 provider is configured and active, follow the instructions in the FIPS compliance tab.

Try It Out

Prerequisites: A TensorFlow SavedModel on disk.

Start TensorFlow Serving with your model mounted:

docker run -p 8500:8500 -p 8501:8501 \
  --mount type=bind,source=/path/to/models,target=/models/my_model \
  -e MODEL_NAME=my_model \
  reg.mini.dev/tensorflow-serving-fips

Check that the model is loaded and ready:

curl http://localhost:8501/v1/models/my_model

You should see a similar confirmation:

{
  "model_version_status": [
    {
      "version": "1",
      "state": "AVAILABLE",
      "status": {}
    }
  ]
}

Send a prediction request via the REST API:

curl -d '{"instances": [[1.0, 2.0, 3.0]]}' \
  -X POST http://localhost:8501/v1/models/my_model:predict

Technical Considerations

The TensorFlow Serving FIPS image provided by Minimus is a FIPS-validated, slim, security-hardened alternative to the public image. The images are largely interchangeable, with a few differences as noted below.

TensorFlow Serving FIPS built by Minimus:

Port 8500 exposes the gRPC endpoint and port 8501 exposes the REST endpoint.
Drill down on the version specification tab to see the default user, listening ports, entrypoint, volumes, environment variables, etc.

The Payoff

A hardened, minimal image that will remain more secure for the long run and accrue vulnerabilities at a slower rate.

See the risk reduction dashboard for a detailed CVE comparison over the past 30 days.
Review the compliance report to see the default hardening and security configurations for the image.

Terms & Info

Trademark

This catalog is published by Minimus. All product names, logos, and marks, other than those belonging to Minimus, shown are owned by their respective rights holders and appear here only to identify the open source software each image contains. Minimus claims no ownership of those marks and implies no affiliation with, endorsement by, certification by, or sponsorship by any rights holder.

Disclaimer

Images are provided "as-is" without warranty of any kind. "Hardened" refers to the security configuration applied at the time of build and does not constitute a guarantee of ongoing security or absence of vulnerabilities. The free tier is provided without support, SLA, or guaranteed patching timelines. Security updates may be applied to paid subscriptions before or instead of free tier images. By pulling or using any image you agree to our Terms of Use.