Patent · US Active

Detection of machine learning model attacks obfuscated in unicode

US12273381B1 · kind B1 · utility

0Cited by
7References
23Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 12, 2024
Grant dateApr 8, 2025
Priority date
Expiry dateNov 12, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/284
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A prompt for a generative artificial intelligence (GenAI) model which contains unicode is received. The prompt is then tokenized to result in a plurality of tokens. Token forming part of a repeating sequence are identified and then removed to result in a modified set of tokens. The modified set of tokens are subsequently detokenized to result in a modified prompt. It is then determined, whether ingestion of the modified prompt by the GenAI model will result in the GenAI model behaving in an undesired manner. The modified prompt is passed to the GenAI model when it is determined that ingestion of the modified prompt will not result in the GenAI model behaving in an undesired manner. Otherwise, at least one remediation action is initiated when it is determined that ingestion of the modified prompt by the GenAI model will result in the GenAI model behaving in an undesired manner.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.