US 12,273,372 B1
Techniques for detecting artificial intelligence model cybersecurity risk in a computing environment
Amitai Cohen, Kfar Saba (IL); Barak Sharoni, Tel Aviv (IL); Shir Tamari, Tel Aviv (IL); George Pisha, Giv'atayim (IL); Itay Arbel, Tel Aviv (IL); Daniel Velikanski, Tel Aviv (IL); and Yaniv Shaked, Tel Aviv (IL)
Assigned to Wiz, Inc., New York, NY (US)
Filed by Wiz, Inc., New York, NY (US)
Filed on Sep. 18, 2024, as Appl. No. 18/888,967.
Application 18/888,967 is a continuation of application No. 18/647,876, filed on Apr. 26, 2024.
Application 18/647,876 is a continuation of application No. 18/584,659, filed on Feb. 22, 2024, granted, now 12,003,529, issued on Jun. 4, 2024.
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01)
CPC H04L 63/1441 (2013.01) [H04L 63/1433 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A method for detecting a cybersecurity risk of an artificial intelligence (AI), comprising:
generating an inspectable disk based on a disk of a resource, the resource deployed in a computing environment;
inspecting the inspectable disk for an AI model deployed on the resource;
generating a representation of the AI model in a security database, the security database including a representation of the computing environment;
detecting sensitive data on which the AI model is trained;
determining that the AI model includes a cybersecurity issue;
generating a representation of the sensitive data in the security database, the representation of the sensitive data connected to the representation of the AI model, in response to detecting the sensitive data; and
initiating a mitigation action based on the cybersecurity issue and the detected sensitive data.