MicrosoftGranted patentSecurity & privacyInterest 7/10

Microsoft patents video verification to confirm real people in clips

This patent describes a system that checks if a person in a video is real by comparing a secure, signed frame from a camera to a potentially edited version. It uses machine learning to match the person's face or body across both frames and adds a digital signature to prove the content is authentic.

Why it mattersThis could help viewers trust that the people they see in videos are actually there, reducing the spread of fake or manipulated media.

In the filing’s own words

Various embodiments of the technology described herein relate to distribution-verified and authenticated content, including obtaining content and authentication data from a user device, authenticating the content based on the authentication data, and distributing the content, including an indication that the content has been verified and/or authenticated. For example, an entity depicted in the content is verified, and data depicting the entity (e.g., video and/or audio) is authenticated and distributed to various user devices.

What exactly they claim (claim 1)

1. A system comprising: a memory component; and a processing device coupled to the memory component, the processing device being implemented by one or more processors to perform operations comprising: obtaining a signed video frame and a manipulated video frame, wherein the signed video frame is generated within a secure environment of a user device; authenticating a first digital signature associated with the signed video frame; causing a first machine learning model to compare a first region of interest in the signed video frame and a second region of interest in the manipulated video frame to determine that an entity depicted in the signed video frame and the manipulated video frame match; generating, based on determining that the entity depicted in the signed video frame and the manipulated video frame match, a second digital signature for the manipulated video frame; and transmitting, to an application executed by a second user device, the second digital signature and the manipulated video frame.

Facts

Company
Microsoft (Microsoft Technology Licensing, LLC)
Official title
Detecting generative machine learning model content
Patent number
US12792780B2
Application number
18668948
Filed
May 20, 2024
Granted
Nov 10, 2026
Inventors
4
Claims
20

Classified under

G06F 21/64 Physics & computingG06V 40/172 Physics & computingH04L 9/3247 Electricity & electronicsH04N 7/15 Electricity & electronics

More from Microsoft in Security & privacy

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.