Security scoring for typographical errors using probabilistic model

ChangeBridge: Patent Grants - Networking (H04L)

Published March 31st, 2026

Detected March 31st, 2026

Summary

USPTO granted patent US12592965B2 to Microsoft Technology Licensing, LLC for a system and method of generating transformation error probabilities to predict typographical errors using a probabilistic graphical model. The patent covers security scoring based on character-by-character transformation analysis of training data containing historical typographical errors.

View original document View source feed page

What changed

USPTO issued patent US12592965B2 titled 'Security scoring for typographical errors' to Microsoft Technology Licensing, LLC (inventors: Laurent Boué, Kiran Rama). The patent describes a computing system that generates transformation error probabilities by analyzing training strings from historical datasets containing typographical errors, populates a probabilistic graphical model with these probabilities, and predicts the likelihood that an input string contains a typographical error. The invention is classified under CPC H04L 63/1483 and contains 14 claims.

Patent grants establish enforceable intellectual property rights. Competitors developing similar typographical error detection or security scoring systems should review the 14 granted claims to assess potential infringement risks and determine whether licensing from Microsoft Technology Licensing, LLC is necessary. The patent claims priority from application filed July 6, 2023.

Source document (simplified)

← USPTO Patent Grants

Security scoring for typographical errors

Grant US12592965B2 Kind: B2 Mar 31, 2026

Assignee

Microsoft Technology Licensing, LLC

Inventors

Laurent Boué, Kiran Rama

Abstract

A computing system generates transformation error probabilities by analyzing a training data set containing training strings, each transformation error probability indicating a probability that a per-character transformation applied to a character of a training string results in a typographical error in a resulting transformation string, wherein the training data set includes strings from a historical dataset of strings including typographical errors. The computing system populates a probabilistic graphical model with the transformation error probabilities corresponding to each resulting transformation string and predicts a likelihood that an input string contains a typographical error based on the probabilistic graphical model.