• Home
  • Search
  • Adversarial Example Generation Method Based on Wavelet Transform
  • https://doi.org/10.3390/info17020182Copy DOI Icon

Adversarial Example Generation Method Based on Wavelet Transform

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

Adversarial examples are crucial tools for assessing the robustness of deep neural networks (DNNs) and revealing potential security vulnerabilities. Adversarial example generation methods based on Generative Adversarial Networks (GANs) have made significant progress in generating image adversarial examples, but still suffer from insufficient sparsity and transferability. To address these issues, this study proposes a novel semi-white-box untargeted adversarial example generation method named Wavelet-AdvGAN, with an explicit threat model defined as follows. Specifically, the attack is strictly untargeted without predefined target categories, aiming solely to mislead DNNs into classifying adversarial examples into any category other than the original label. It adopts a semi-white-box setting where attackers are denied access to the target model’s private information. Regarding the generator’s information dependence, the training phase only utilizes public resources (i.e., the target model’s public architecture and CIFAR-10 public training data), while the test phase generates adversarial examples through one-step feedforward of clean images without interacting with the target model. The method incorporates a Frequency Sub-band Difference (FSD) module and a Wavelet Transform Local Feature (WTLF) extraction module, evaluating the differences between original and adversarial examples from the frequency domain perspective. This approach constrains the magnitude of perturbations, reinforces feature regions, and further enhances the attack effectiveness, thereby improving the sparsity and transferability of adversarial examples. Experimental results demonstrate that the Wavelet-AdvGAN method achieves an average increase of 1.26% in attack success rates under two defense strategies—data augmentation and adversarial training. Additionally, the adversarial transferability improves by an average of 2.7%. Moreover, the proposed method exhibits a lower l0 norm, indicating better perturbation sparsity. Consequently, it effectively evaluates the robustness of deep neural networks.

Similar Papers
  • Conference Article

Dynamic Decision Boundaries for Improved Robustness against Adversarial Attacks

  • Feb 24, 2023
  • Zeyu Long
  • Conference Article
  • Citations14

ALA: Naturalness-aware Adversarial Lightness Attack

  • Oct 26, 2023
  • Yihao Huang +7
  • Research Article
  • Citations215

Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Minhao Cheng +4
  • Conference Article

Understanding adversarial robustness on the hypersphere

  • Jun 08, 2023
  • Zitian Zhao
  • Conference Article
  • Citations7

Assessing transferability of adversarial examples against malware detection classifiers

  • Apr 30, 2019
  • Yixiang Wang +2
  • Video Transcripts

On the Transferability of Adversarial Attacks against Neural Text Classifier

  • Oct 15, 2021
  • Underline Science Inc.
  • Liping Yuan
  • Conference Article
  • Citations3

Defending Against Adversarial Examples via Soft Decision Trees Embedding

  • Oct 15, 2019
  • Yingying Hua +4
  • Book Chapter
  • Citations4

BeamAttack: Generating High-quality Textual Adversarial Examples Through Beam Search and Mixed Semantic Spaces

  • Jan 01, 2023
  • Hai Zhu +2
  • Conference Article

Regional Saliency Map Attack for Medical Image Segmentation

  • Oct 16, 2022
  • Pei Yang +1
  • Research Article
  • Citations5

Crafting Transferable Adversarial Examples Against Face Recognition via Gradient Eroding

  • Jan 01, 2024
  • IEEE Transactions on Artificial Intelligence
  • Huipeng Zhou +6
  • Research Article
  • Citations134

Self-Attention Context Network: Addressing the Threat of Adversarial Attacks for Hyperspectral Image Classification.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Yonghao Xu +2
  • Conference Article
  • Citations6

Accelerating Spectral Normalization for Enhancing Robustness of Deep Neural Networks

  • Jul 01, 2021
  • Zhixin Pan +1
  • Research Article
  • Citations17

Generating adversarial examples via enhancing latent spatial features of benign traffic and preserving malicious functions

  • Dec 31, 2021
  • Neurocomputing
  • Rongqian Zhang +4
  • Conference Article
  • Citations7

FuzzGAN: A Generation-Based Fuzzing Framework for Testing Deep Neural Networks

  • Dec 01, 2022
  • Ge Han +4
  • PDF
  • Research Article
  • Citations2

Efficient Adversarial Attack Based on Moment Estimation and Lookahead Gradient

  • Jun 24, 2024
  • Electronics
  • Dian Hong +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.