Patent · US Active

System and method for detecting adversarial attacks

US11462211B2 · kind B2 · utility

0Cited by
0References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 9, 2020
Grant dateOct 4, 2022
Priority date
Expiry dateAug 13, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2015/225
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A linguistic system for transcribing an input, where the linguistic system comprises a processor configured to execute a neural network multiple times while varying weights of at least some nodes of the neural network to produce multiple transcriptions of the input. Further, determine a distribution of pairwise distances of the multiple transcriptions; determine a legitimacy of the input based on the distribution; and transcribe the input using stored weights of the nodes of the neural network when the input is determined as legitimate to produce a final transcription of the input.

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