Overview
Protect model weights on GPUs — sealed to hardware, decrypted only in VRAM, released only under policy you can verify.
What this protects
Model weights are the asset. On a shared or rented GPU, they normally sit in plain memory the moment inference runs — copyable by anyone with host access. SCSA seals the weights to the attested silicon of a specific GPU: they are decrypted only inside the GPU's VRAM, only after the hardware proves itself, and only while policy holds. Off that GPU — copied to disk, another card, or a cloud bucket — they are noise.
The same cryptographic core as SCSA Vault, pointed at the GPU: keys are derived from a live hardware measurement at access time, never stored.
The four things it does
Bind weights to the GPU
Keys derive from the GPU's attestation measurement. Move the model to another card and decryption fails — the key can't leave the silicon it was bound to.
Decrypt only in VRAM
Weights are decrypted on the GPU and consumed there. The plaintext never lands in host memory; only results leave the device.
Split the key across parties
Threshold custody: no single party — not even the operator — can unseal alone. Any party can revoke and make the model permanently unrecoverable.
Prove it, don't assert it
Every property is a live, externally verifiable proof: attestation, anti- replay, in-VRAM consumption, revocation, and a transparent STARK audit stream.
Two ways to run it
- Managed / bring-your-own-GPU — register a GPU by SSH endpoint and drive it through the control plane. See Bring your own GPU.
- Sovereign / self-hosted — the CLI drives your GPU directly, with your key, and nothing passes through anyone else's infrastructure. See Sovereign mode.
The security rests on the math — hardware-signed attestation and threshold custody — not on trusting whoever holds the SSH key. That principle runs through every mode below.
Start here
The scsa CLI is the primary interface. Install it, point it at a
GPU (yours or one you rent), and run the live proofs:
npm install -g @sevenlayer/scsa
scsa gpu register gpu01.internal 22 # bring your own GPU
scsa gpu deploy <id>
scsa prove <id> # run the live security proofs