How it works

Simplified illustration · invented question and data

Follow one AI question: what protects it, step by step.

To answer a question, an AI service normally decrypts it, so whoever runs the server can read it. Two techniques change that: homomorphic encryption (HE) for small, exact tasks, and a trusted execution environment (TEE) for the model itself. Five steps show where each one fits.

Five steps

The question (invented) Under which rules may we onboard Kestrelmoor Handels AG?

01 The question

What protects it: homomorphic encryption (HE)

The company in the question is checked without being revealed.

You write the question in your browser; the company it names is encrypted there and checked against a sanctions list with homomorphic encryption, so the service compares it without decrypting it.

Demo · sample list BlindScreen This step on its own: check a name against a list under encryption. Exact spelling only. Try BlindScreen

03 The answer

What protects it: a trusted execution environment (TEE)

The model writes the answer in hardware-isolated memory.

Homomorphic encryption cannot run a language model today: it is far too slow and suits only small, exact tasks, so this step needs a trusted execution environment, where the model runs in hardware-isolated memory and the machine’s host sees that memory only encrypted.

A TEE keeps the machine’s host out; it does not hide the question from the model inside.

Live TAIA Confidential Ask This step as a service: a language model answers your question on a confidential node. Ask a question, free

04 The return

What protects it: encryption only your browser can open

The answer comes back, and only you open it.

The answer leaves the isolated memory encrypted for your browser alone, travels back that way, and only your browser opens it with your key.

05 The decision and the audit

What protects it: a record of the grounds (Atelier), and homomorphic encryption for the audit (HE)

The decision is recorded; an auditor checks without seeing the data.

When you decide, what the decision rests on is recorded (TAIA Atelier keeps such records); later an auditor can check the encrypted records with homomorphic encryption without seeing the data.

TAIA Atelier’s records do not use homomorphic encryption; an audit under encryption is not available.

Simplified illustration. The locked text is a picture, not real ciphertext; the question, the company, the notes and the answer are invented.

Live: TAIA Confidential Screening Step 1 as a product: check a name against the SECO, EU and OFAC sanctions lists. Your browser encrypts the name; TAIA’s service compares it without decrypting it. Check a name
The idea as a picture: The Locked Question

Plainly

What you can try now, what is under research, and the limits.

Now

TAIA Confidential Screening (step 1 as a product) is live: it checks a name against the SECO, EU and OFAC sanctions lists. BlindScreen (step 1) runs homomorphic encryption in your browser and on TAIA’s service, with a sample list. Exact spelling only.

Under research

VaultSearch (step 2) is a demo. TAIA Confidential Ask (step 3) is live.

Limits

No language model under homomorphic encryption: it is far too slow for that today. For the model’s machine, TAIA can show only what GKE’s node label says, not an independent check (attestation). Matching under encryption needs the exact spelling.

Simplified illustration · invented question and data. This page sends nothing and stores nothing.