Today
TAIA Screening, in development: names compared in plain text with tolerant matching; not live.
In that design the service sees the names, and none of it uses homomorphic encryption. TAIA does not run this in a product today.
Research
Research demo · synthetic data · not a TAIA product feature
Ask without being seen.
Homomorphic encryption lets a service compute on data it cannot read. Your question goes out locked, the work happens on the locked version, and the answer comes back locked. Only your key opens it. This page shows the idea, then the first place TAIA is researching it: checking a name against a list that neither side shows the other.
Start with the idea01 The idea
Type any question, lock it, let the service turn it, then solve it with your key. Watch what the service holds while it works.
Your key stays here.
—
Idle
This is an illustration. The cube and the scrambled text are pictures, not real ciphertext. Real encryption shows no pattern at all. Running a full language-model conversation under homomorphic encryption is still far too slow for daily use; it is a research question.
02 Where TAIA starts
An institution needs to know whether a client’s name is on a list held by someone else. It should not reveal the name. The list holder should not reveal the list. Real names are written many ways, and that is the hard part.
1 · Pick an invented client name
2 · Pick an approach
—
All names and the list are invented for this page. The verdicts above show the logic of each approach; they are not measured results.
From TAIA’s research bench, on invented names, one run per cell: A found 88.7% of matching names at 10,000 list entries and 86.4% at 50,000, and raised an alert on 10.9% and 20.0% of non-matching names; B found 26.0% at both sizes, with 0.0% false matches.
03 In a decision record
If the research works, one line in a decision record could say that a screening ran without the name leaving the institution. This is a design, not a feature.
The result line follows the name and approach you picked above.
04 Plainly
TAIA Screening, in development: names compared in plain text with tolerant matching; not live.
In that design the service sees the names, and none of it uses homomorphic encryption. TAIA does not run this in a product today.
A research bench on invented names: approach A in plain text, approach B with the open-source Microsoft APSI library, on a CPU, one run per cell, written up. Not deployed, not connected to any product.
Approach C, tolerant matching under encryption, is an open research question. TAIA is looking for an academic research partner for it. No date is promised.