Nvidia patents AI tool that finds security flaws in system diagrams
Nvidia describes a system that uses AI to analyze diagrams and documents about a computer system's design. It converts these visual and text inputs into data that a generative AI model can use to identify potential security threats.
In the filing’s own words
Disclosed are systems and techniques for threat modeling with artificial intelligence. The techniques include providing a first subset of a plurality of content items related to a target system architecture as input to a diagram parser to obtain a diagram parser output. The techniques further include providing the diagram parser output and a second subset of the plurality of content items as input to a first artificial intelligence (AI) embedding model to obtain a first AI embedding model output comprising encoded representations of the diagram parser output and the second subset of the plurality of content items. The techniques further include providing at least a first portion of the encoded representations of the diagram parser output and the second subset of the plurality of content items as input to a first generative AI model to obtain a plurality of potential threats related to the target system architecture.
What exactly they claim (claim 1)
1. A system comprising: a memory; and one or more processors, coupled to the memory, to: provide a first subset of a plurality of content items related to a target system architecture as input to a diagram parser to obtain a diagram parser output; provide the diagram parser output and a second subset of the plurality of content items related to the target system architecture as input to a first artificial intelligence (AI) embedding model to obtain a first AI embedding model output comprising encoded representations of the diagram parser output and the second subset of the plurality of content items related to the target system architecture; and provide at least a first portion of the encoded representations of the diagram parser output and the second subset of the plurality of content items related to the target system architecture as input to a first generative AI model to obtain a plurality of potential threats related to the target system architecture.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- THREAT MODELING WITH ARTIFICIAL INTELLIGENCE
- Publication number
- US20260330024A1
- Application number
- 19186538
- Filed
- Apr 22, 2025
- Published
- Oct 22, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06F 21/577 Physics & computingG06F 2221/034 Physics & computingMore from Nvidia in Security & privacy
- Nvidia patents chip protection against clock speed attacks Sep 22, 2026
- Nvidia patents secure way for virtual apps to use encryption keys Oct 6, 2026
- Nvidia patents hardware method to keep encryption keys hidden from software Oct 13, 2026
- Nvidia patents system that checks secret passwords against rules Sep 3, 2026
- Nvidia patents database search that hides restricted data in real time Sep 17, 2026
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.