Get the newsletter
IBM · Security · Filed May 16, 2025 · USPTO published Nov 19, 2026 · This week's release

IBM Files Patent for Training AI on Data It Never Reads in Plain Text

IBM describes an AI model that learns from scrambled text and answers scrambled questions, so the readable version never sits on the server. Only a device with the right key can read the reply.

A computer teaches an AI using coded records so the program learns without ever seeing personal details. Drawing from patent filing US 2026/0368625 A1.
A computer teaches an AI using coded records so the program learns without ever seeing personal details.All 9 drawings ↓
Publication number
US 2026/0368625 A1(US20260368625A1)
Applicant
International Business Machines Corporation
Filed · Published
May 16, 2025 · Nov 19, 2026
Inventors
Hirenkumar Ashokbhai THUMMAR, Linda Ha KATO, Chad Eric DeLUCA, Daniel GRUHL, Shubhi ASTHANA, Pawan Raghunath CHOWDHARY, Steven R. WELCH, Anna Lisa GENTILE, Bing ZHANG, Alfredo ALBA
Status when we published
Waiting for an examiner
Document
20 claims
US classification
706/12

What IBM's scrambled-data AI training does

Right now, teaching an AI model with sensitive documents usually means unlocking them first. That puts things like medical records, personal details or company secrets in readable form on servers that may belong to someone else. IBM's patent application describes a way to skip that unlocking step.

The system scrambles the training text with a secret key, then trains the AI on the scrambled version. When you ask a question, your question gets scrambled the same way, the AI works out an answer, and the answer comes back still scrambled. Only a device holding the right key can turn it into readable words.

If your device lacks the key, you get an error message instead of an answer. The filing also describes handing different groups different keys, so each group can read only the pieces meant for it.

From the filing · CLAIM 1
… training a machine learning model with the encrypted training data to generate a trained machine learning model …

Translation: The system teaches the AI using only scrambled information so it never sees the raw data.

How a scrambled question reaches an answer

The core claim is a pipeline with encryption on both ends. The system encrypts training data, trains a machine learning model on that encrypted version, encrypts each incoming query, runs it through the model, and sends back an encrypted result. The user's device then decrypts that result with its private keys.

The favored scrambling method is format-preserving encryption (scrambled text keeps the same shape as the original, so a string of characters becomes another string of characters). The filing names a Feistel-based version, which splits the data into two halves and runs it through rounds of substitution and shuffling that a secret key can reverse. Because the shape survives, a simple bag-of-words model (one that tracks which words appear and ignores their order) can still learn from it.

Search works by scrambling a keyword the same way, then matching it against the scrambled text without decrypting anything. The filing also describes:

  • Encrypting with multiple keys, so different user groups can read only their own portions
  • Splitting the training data into segments, each locked with a different set of keys
  • Swapping characters or sensitive items like card numbers for tokens (stand-in values)
  • Homomorphic encryption (doing math directly on locked data) as another option

Why medical and secret records come into it

If it works as described, a hospital, a company or a government office could let an AI model learn from sensitive files on shared cloud servers without readable text ever sitting there. The filing names medical records, classified documents and personal details like card and Social Security numbers as target uses. For you, that means fewer places where your private information is exposed in readable form.

The filing also says the approach could cover large language models (the technology behind chatbots), and could protect a shrunken model downloaded to a smartphone, so a stolen copy would be useless without the key. It extends the idea to features pulled from images and sound too. Keep in mind this is an application with no performance numbers, so how well a model actually learns from scrambled data remains open.

This is the 14th IBM filing we've tracked since July in our on-device AI privacy watchlist, after earlier applications to shield company data from AI and test apps on scrubbed real data.

Source: US 2026/0368625 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time IBM patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 9 sheets

9 drawing sheets from US 2026/0368625 A1 · click any drawing to enlarge

Network hardware and cloud servers running privacy software, drawing sheet 1 from US 2026/0368625 A1
Sheet 1 Network hardware and cloud servers running privacy software
A server receives training files from a user, drawing sheet 2 from US 2026/0368625 A1
Sheet 2 A server receives training files from a user
Scrambling the training records before use, drawing sheet 3 from US 2026/0368625 A1
Sheet 3 Scrambling the training records before use
Teaching the AI model on fully encrypted information, drawing sheet 4 from US 2026/0368625 A1
Sheet 4 Teaching the AI model on fully encrypted information
An incoming user prompt gets locked with encryption, drawing sheet 5 from US 2026/0368625 A1
Sheet 5 An incoming user prompt gets locked with encryption
Generating hidden answers directly from locked questions, drawing sheet 6 from US 2026/0368625 A1
Sheet 6 Generating hidden answers directly from locked questions
Unlocking the model's final response on your device, drawing sheet 7 from US 2026/0368625 A1
Sheet 7 Unlocking the model's final response on your device
Showing an error when the secure decryption fails, drawing sheet 8 from US 2026/0368625 A1
Sheet 8 Showing an error when the secure decryption fails
Show the other 1 sheets
How the AI trains and answers using encrypted data, drawing sheet 9 from US 2026/0368625 A1
Sheet 9 How the AI trains and answers using encrypted data
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.