USPTO Grants Patent for Secure Statistical Classifier Generation

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted a patent (US12585988B2) to NEC Corporation of America for systems and methods for generating and applying a secure statistical classifier. The patent, filed on March 1, 2022, details a process involving cryptographic keys to create unique trained sub-classifiers.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585988B2 to NEC Corporation of America. This patent covers "Systems and methods for generating and applying a secure statistical classifier." The core innovation involves using cryptographic keys to create unique trained sub-classifiers from an untrained statistical classifier, enhancing security in machine learning applications. The filing date for this patent was March 1, 2022, and it was granted on March 24, 2026.

This patent grant is primarily an intellectual property development and does not impose new regulatory obligations on companies. However, it signifies a technological advancement in secure AI and machine learning that may influence future product development and competitive landscapes. Companies operating in AI and data analytics should be aware of this patented technology, particularly if developing or utilizing secure statistical classification methods.

Source document (simplified)

← USPTO Patent Grants

Systems and methods for generating and applying a secure statistical classifier

Grant US12585988B2 Kind: B2 Mar 24, 2026

Assignee

NEC Corporation Of America

Inventors

Jun Furukawa, Joseph Keshet, Kazuma Ohara, Toshinori Araki, Hikaru Tsuchida, Takuma Amada, Kazuya Kakizaki, Shir Aviv-Reuven

Abstract

There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, wherein the statistical classifier includes the plurality of trained sub-classifiers.