The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Nov. 10, 2026

Filed:

Oct. 23, 2024
Applicant:

Zscaler, Inc., San Jose, CA (US);

Inventors:

Chenhui Hu, Boston, MA (US);

Weizhen Liu, San Jose, CA (US);

Miao Zhang, Sunnyvale, CA (US);

Assignee:

Zscaler, Inc., Santa Clara, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
H04L 9/40 (2022.01);
U.S. Cl.
CPC ...
H04L 63/1416 (2013.01); H04L 63/145 (2013.01);
Abstract

Large Language Model (LLM) security includes monitoring an LLM; detecting an attack on the LLM and defining an attack type of a plurality of attack types based on the monitoring, providing a notification of the attack; and causing a defense to the attack based on the attack type. Advantageously, the security can be configured to be executed between a user outside of the LLM. Further, the security can be configured to defend against multi-turn attacks.


Find Patent Forward Citations

Quick Actions:

Hu, Chenhui. (2026). Vulnerabilities and protections in large language models (U.S. Patent No. 12794906). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12794906

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…