Systeme und Verfahren zur Sicherung von Modellen Künstlicher Intelligenz für den Benutzer

Details

Veröffentlichungs-Nr.

EP4776166

Anmeldetag

6. Januar 2026

Veröffentlichung

15. Juli 2026

Rechtsraum

EP

Abstract

Aspects of this disclosure relate to systems and methods for preventing injection attacks to large language models (LLMs). Techniques implemented by these systems and methods can include obtaining a query from a user device that is configured to cause an LLM to generate an output outside of a predetermined scope. In response to obtaining the query, systems can execute one or more evaluation models that are configured to identify one or more compatibility issues that can arise if the queries are executed by an LLM. Where a query is identified as having one compatibility issue(s), the systems described herein can either update the query to address the issue. Additionally, or alternatively, the systems described herein can prevent the processing of the query (and processing in furtherance of the injection attack) by an LLM.

Anmelder

Firma

Capital One Services, LLC

Land

🇺🇸 USA