• Home
  • Search
  • Generating watermarked adversarial texts
  • Cite Icon1
  • https://doi.org/10.1117/1.jei.32.2.023023Copy DOI Icon

Generating watermarked adversarial texts

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

Adversarial example generation (AEG) has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models. Due to the extensiveness and high liquidity of natural language over the social networks, various natural language-based adversarial attack algorithms have been proposed in the literature. These algorithms generate adversarial text examples with high semantic quality. However, the generated adversarial text examples and the corresponding attack models may be maliciously or illegally used. To tackle this problem, we present a general framework encapsulated in the cloud application programming interfaces (APIs) for generating watermarked adversarial text examples to protect adversarial text examples and corresponding adversarial text attack models. For each word in a given text, a set of candidate words are determined to ensure that all the words in the set can be used to carry secret bits or facilitate the construction of adversarial example. By applying a word-level adversarial text generation algorithm, the watermarked adversarial text example can be finally generated. Experiment results show that the adversarial text examples generated by the proposed method not only successfully fool advanced DNN models, but also carry watermarks that can effectively verify the ownership and trace the source of the adversarial examples and the corresponding attack models. Moreover, the watermark can still survive after attacked with AEG algorithms, which has shown the applicability and superiority.

Similar Papers
  • 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
  • Citations7

Automatic Generation of Adversarial Readable Chinese Texts

  • Mar 01, 2023
  • IEEE Transactions on Dependable and Secure Computing
  • Mingxuan Liu +7
  • Research Article
  • Citations2

Restoration of Adversarial Examples Using Image Arithmetic Operations

  • Jan 01, 2022
  • Intelligent Automation & Soft Computing
  • Kazim Ali +1
  • Conference Article
  • Citations3

How Robust is Your Automatic Diagnosis Model?

  • Nov 01, 2019
  • Ke Wang +3
  • Research Article
  • Citations11

Efficiently generating sentence-level textual adversarial examples with Seq2seq Stacked Auto-Encoder

  • Nov 03, 2022
  • Expert Systems with Applications
  • Ang Li +5
  • Research Article
  • Citations90

Analyzing the Noise Robustness of Deep Neural Networks.

  • Jan 23, 2020
  • IEEE Transactions on Visualization and Computer Graphics
  • Kelei Cao +5
  • Conference Article
  • Citations56

Analyzing the Noise Robustness of Deep Neural Networks

  • Oct 01, 2018
  • Mengchen Liu +4
  • Book Chapter
  • Citations22

Adversarial Examples in Deep Neural Networks: An Overview

  • Oct 24, 2019
  • Emilio Rafael Balda +2
  • Research Article
  • Citations7

Improving the Transferability of Adversarial Attacks on Face Recognition With Beneficial Perturbation Feature Augmentation

  • Dec 01, 2024
  • IEEE Transactions on Computational Social Systems
  • Fengfan Zhou +5
  • Conference Article
  • Citations12

Nickel to Lego

  • Nov 06, 2019
  • Joon Kuy Han +2
  • Conference Article
  • Citations10

Fooling a Neural Network in Military Environments: Random Untargeted Adversarial Example

  • Oct 01, 2018
  • Hyun Kwon +3
  • Research Article

A spatial-frequency domain joint detection method of adversarial examples for signal modulation recognition network

  • Mar 23, 2026
  • Cybersecurity
  • Wenlin Liu +5
  • Research Article
  • Citations3

FCDM: A Methodology Based on Sensor Pattern Noise Fingerprinting for Fast Confidence Detection to Adversarial Attacks

  • Jan 31, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Yazhu Lan +6
  • Conference Article
  • Citations5

Combating Multi-level Adversarial Text with Pruning based Adversarial Training

  • Jul 18, 2022
  • Jianpeng Ke +3
  • 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
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.