/Patent Tracker
NvidiaPatent applicationAI & softwareInterest 6/10

Nvidia patents system to test AI models against simulated security attacks

Patent drawing
Patent drawing from the official filing.

Nvidia describes a method for creating a library of potential security threats specific to an AI model. The system categorizes these risks and uses them to generate simulated attacks to test the model's defenses.

Why it mattersThis is interesting for tech security professionals because it automates the process of stress-testing AI systems against known vulnerabilities before they are deployed.

In the filing’s own words

Devices, systems, and techniques for assessing and managing security risk scenarios associated with an artificial intelligence (AI) model executed by a primary computing system. The techniques include generating, based on a set of security-related data associated with an AI model, a library comprising a set of identified ai security risk scenarios associated with the AI model. The techniques include classifying, based on a set of AI model criteria, a first identified security risk scenario of the set of identified security risk scenarios into a first category of a set of categories to generate a first classified security risk scenario. The techniques include causing a simulated security attack associated with the computing system to be created based on the first classified security risk scenario.

What exactly they claim (claim 1)

1. A method comprising: generating, based on a set of security-related data associated with an artificial intelligence (AI) model, a library comprising a set of identified security risk scenarios associated with the AI model executable by a computing system; classifying, based on a set of AI model criteria, a first identified security risk scenario of the set of identified security risk scenarios into a first category of a set of categories to generate a first classified security risk scenario; and causing a simulated security attack associated with the computing system to be created based on the first classified security risk scenario.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
SECURITY RISK SCENARIO LIBRARY GENERATION
Publication number
US20260310791A1
Application number
19171820
Filed
Apr 7, 2025
Published
Oct 8, 2026
Inventors
1
Claims
20

Classified under

G06F 21/577 Physics & computingG06F 2221/034 Physics & computing

More from Nvidia in AI & software

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.