cyntrisec/confidential-ml-transport

Attestation-bound encrypted tensor transport for confidential ML inference over VSock/TCP. Binary framing, X25519+ChaCha20Poly1305 AEAD, 3-message attested handshake.

32
/ 100
Emerging

This is a specialized software component for developers who are building applications that use machine learning (ML) models in a secure, confidential environment, often referred to as a Trusted Execution Environment (TEE). It allows these applications to send and receive ML data, like tensors, across a network securely. The data is encrypted and authenticated, ensuring that only verified, legitimate ML services can process it.

Use this if you are a developer building a confidential ML inference service where securing the data in transit between a client and a TEE-based ML model is paramount, protecting sensitive intellectual property or private user data.

Not ideal if you need a general-purpose networking library for non-confidential data or if your ML workflow does not involve Trusted Execution Environments.

confidential-computing machine-learning-inference secure-data-transport trusted-execution-environment application-security
No Package No Dependents
Maintenance 10 / 25
Adoption 11 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Rust

License

Apache-2.0

Last pushed

Mar 09, 2026

Monthly downloads

514

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cyntrisec/confidential-ml-transport"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.