• Home
  • Search
  • Watermarking of Deep Recurrent Neural Network Using Adversarial Examples to Protect Intellectual Property
  • Cite Icon8
  • https://doi.org/10.1080/08839514.2021.2008613Copy DOI Icon

Watermarking of Deep Recurrent Neural Network Using Adversarial Examples to Protect Intellectual Property

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

ABSTRACT In the present era, deep learning algorithms are the key elements of several state-of-the-art solutions. But developing these algorithms for production requires a huge volume of data, computational resources, and human expertise. Thus, illegal reproduction, distribution, and modification of these models can cause economic damage to developers and can lead to copyright infringement. We propose a novel watermarking algorithm for deep recurrent neural networks based on adversarial examples that can verify the ownership of the model in a black-box way. In this paper, a novel algorithm to watermark a popular pre-trained speech-to-text deep recurrent neural network model Deep Speech without affecting the accuracy of the model is demonstrated. Watermarking is done by generating a set of adversarial examples by adding noise to the input such that the DeepSpeech model predicts the given input as the target string. In the case of copyright infringement, these adversarial examples can be used to verify ownership of the model. If the alleged stolen model predicts the same target string for the adversarial examples, the ownership of the model is verified. This novel watermarking algorithm can minimize the economic damage to the owners of the deep learning models due to stealing and plagiarizing.

Similar Papers
  • Research Article
  • Citations21

A Simulated Prospective Evaluation of a Deep Learning Model for Real-Time Prediction of Clinical Deterioration Among Ward Patients.

  • Mar 15, 2021
  • Critical Care Medicine
  • Parth K Shah +6
  • Research Article
  • Citations53

An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model.

  • Nov 13, 2021
  • Environmental Monitoring and Assessment
  • Salar Valizadeh Moghadam +5
  • Conference Article
  • Citations4

A Deep Recurrent Neural Network Based Predictive Control Framework for Reliable Distributed Stream Data Processing

  • May 01, 2019
  • Jielong Xu +5
  • Research Article
  • Citations1

Generating watermarked adversarial texts

  • Mar 28, 2023
  • Journal of Electronic Imaging
  • Mingjie Li +3
  • PDF
  • Research Article
  • Citations8

Feasibility of DRNN for Identifying Built Environment Barriers to Walkability Using Wearable Sensor Data from Pedestrians’ Gait

  • Apr 26, 2022
  • Applied Sciences
  • Hyunsoo Kim
  • Research Article
  • Citations1

Generating traceable adversarial text examples by watermarking in the semantic space

  • Nov 26, 2022
  • Journal of Electronic Imaging
  • Mingjie Li +2
  • Research Article

Fusion of deep recurrent neural network models and fuzzy decision support system for tweet sentiment analysis and classification

  • Oct 02, 2025
  • Automatika
  • A Sherin +3
  • Conference Article
  • Citations1

A Deep Recurrent Neural Network Model for affine quasi-LPV System Identification

  • Jul 12, 2022
  • Alexander Rehmer +1
  • Conference Article
  • Citations12

Nickel to Lego

  • Nov 06, 2019
  • Joon Kuy Han +2
  • Research Article
  • Citations32

CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing for Image-Based Deep Learning Systems

  • Nov 01, 2022
  • IEEE Transactions on Software Engineering
  • Pengcheng Zhang +3
  • Research Article
  • Citations89

Predicting heating demand and sizing a stratified thermal storage tank using deep learning algorithms

  • Jun 20, 2018
  • Applied Energy
  • Aowabin Rahman +1
  • Research Article
  • Citations10

AdvEWM: Generating image adversarial examples by embedding digital watermarks

  • Dec 06, 2023
  • Journal of Information Security and Applications
  • Yuexin Xiang +5
  • Conference Article
  • Citations24

Lithium-ion Battery State of Charge Estimation Method Using Optimized Deep Recurrent Neural Network Algorithm

  • Sep 01, 2019
  • M.S Hossain Lipu +5
  • Research Article
  • Citations2

Beat-to-beat continuous blood pressure estimation with optimal feature set of PPG and ECG signals using deep recurrent neural networks

  • Oct 20, 2023
  • Vessel Plus
  • Hanjie Chen +4
  • Research Article
  • Citations75

Deep Learning and Blockchain with Edge Computing for 5G-Enabled Drone Identification and Flight Mode Detection

  • Jan 01, 2021
  • IEEE Network
  • Abdu Gumaei +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.