US 12,273,370 B1
System and method for detecting cybersecurity risks in managed artificial intelligence models
Amitai Cohen, Kfar Saba (IL); Barak Sharoni, Tel Aviv (IL); Alon Schindel, Tel Aviv (IL); Alon Weiss, Tel Aviv (IL); Itay Arbel, Tel Aviv (IL); George Pisha, Giv'atayim (IL); Maayan Laav, Tel Aviv (IL); and Liron Levin, Kfar Saba (IL)
Assigned to Wiz, Inc., New York, NY (US)
Filed by Wiz, Inc., New York, NY (US)
Filed on May 23, 2024, as Appl. No. 18/672,749.
Application 18/672,749 is a continuation of application No. 18/584,670, filed on Feb. 22, 2024, granted, now 12,028,368.
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); G06F 21/62 (2013.01)
CPC H04L 63/1433 (2013.01) [G06F 21/6218 (2013.01); H04L 63/0823 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method for detecting a combined cybersecurity risk for an artificial intelligence (AI) model, comprising:
detecting an AI model deployed in a computing environment;
generating a representation of the AI model in a security database, the security database including a representation of the computing environment;
detecting in the AI model a first cybersecurity object;
detecting in the computing environment a second cybersecurity object;
determining that the AI model is exposed to a toxic combination cybersecurity risk based on the detected first cybersecurity object and the detected second cybersecurity object; and
initiating a mitigation action based on the toxic combination cybersecurity risk.