Invention Grant
- Patent Title: System and method for detecting adversarial attacks
-
Application No.: US16844826Application Date: 2020-04-09
-
Publication No.: US11462211B2Publication Date: 2022-10-04
- Inventor: Jonathan Le Roux , Tejas Jayashankar , Pierre Moulin
- Applicant: Mitsubishi Electric Research Laboratories, Inc.
- Applicant Address: US MA Cambridge
- Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee Address: US MA Cambridge
- Agent Gennadiy Vinokur; Hironori Tsukamoto
- Main IPC: G10L15/16
- IPC: G10L15/16 ; G06F17/16 ; G06K9/62 ; G06N3/08 ; G10L15/22

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.
Public/Granted literature
- US20210319784A1 System and Method for Detecting Adversarial Attacks Public/Granted day:2021-10-14
Information query