Machine Learning Model Parameter Based Encryption Patent Application
Summary
The USPTO has published a patent application (US20260087122A1) detailing a method for encrypting data using machine learning model parameters. The application describes a system that modifies encoder and decoder weights based on generated keys derived from a password to encapsulate and decode data.
What changed
This document is a published patent application from the USPTO, not a regulatory rule or guidance. It describes a novel method for data encryption that leverages machine learning model parameters. The proposed system involves receiving a password to generate a key, which then modifies the weights and biases of an encoder and decoder. This modified encoder-decoder pair is used to encapsulate secondary data within first data, creating an embedding that can be decoded to retrieve the original second data.
As a patent application, this document does not impose any immediate compliance obligations or deadlines on regulated entities. However, it signals potential future technological developments in cybersecurity and data protection that companies, particularly in the technology sector, may wish to monitor. The underlying concepts could influence the development of new encryption standards or security products.
Archived snapshot
Mar 26, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Machine Learning Model Parameter Based Encryption
Application US20260087122A1 Kind: A1 Mar 26, 2026
Inventors
Julian Collado Umana, Andrew Davis
Abstract
A first password is received by a password encoder which uses the first password to generate a first key. This first key is used to modify weights and biases of an encoder to result in a modified encoder. Further, weights and biases of a decoder operating in tandem with the encoder based can be modified based on a second key to result in a modified decoder. First data is received which encapsulates second data in a hidden compartment. The first data is encoded by the modified encoder to result to generate an embedding. The modified decoder decodes the embedding to result in a representation of the second data which, in turn, can be provided to a consuming application or process. The first data can be input into the encoder and the decoder prior to those components being modified to result in a representation of the first data.
CPC Classifications
G06F 21/46 H04L 9/0838 H04L 9/0869 H04L 9/088 H04L 9/14 H04L 63/083
Filing Date
2025-03-28
Application No.
19094688
Related changes
Get daily alerts for USPTO Patent Applications - Networking (H04L)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Networking (H04L) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.