• Home
  • Search
  • ASIGM: An Innovative Adversarial Stego Image Generation Method for Fooling Convolutional Neural Network-Based Image Steganalysis Models
  • Cite Icon2
  • https://doi.org/10.3390/electronics14040764Copy DOI Icon

ASIGM: An Innovative Adversarial Stego Image Generation Method for Fooling Convolutional Neural Network-Based Image Steganalysis Models

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

To defeat AI-based steganalysis systems, various techniques using adversarial example attack methods have been reported. In these techniques, adversarial stego images are generated using adversarial attack algorithms and steganography embedding algorithms sequentially and independently. However, this approach can be inefficient because both algorithms independently insert perturbations into a cover image, and the steganography embedding algorithm could significantly lower the undetectability or indistinguishability of adversarial attacks. To address this issue, we propose an innovative adversarial stego image generation method (ASIGM) that fully integrates the two separate algorithms by using the Jacobian-based Saliency Map Attack (JSMA). JSMA, one of the representative l0 norm-based adversarial example attack methods, is used to compute a set of pixels in the cover image that increases the probability of being classified as the non-stego class by the steganalysis model. The reason for this calculation is that if a secret message is inserted into the limited set of pixels in such a way, noise is only required for message embedding, and even misclassification of the target steganalysis model can be achieved without additional noise insertion. The experimental results demonstrate that our proposed ASIGM outperforms two representative steganography methods (WOW and ADS-WOW).

Loading PDF

Similar Papers
  • Research Article
  • Citations2

Performance Comparison of Adversarial Example Attacks Against CNN-Based Image Steganalysis Models

  • Nov 13, 2025
  • Electronics
  • Hyeonseong Kim +2
  • Research Article

MAFL-Attack: a targeted attack method against deep learning-based medical image segmentation models.

  • Jul 16, 2025
  • Journal of medical imaging (Bellingham, Wash.)
  • Junmei Sun +6
  • Research Article
  • Citations4

Adversarial attack method against image classification based on haze perturbation

  • Feb 01, 2023
  • SCIENTIA SINICA Informationis
  • 伟 冯 +3
  • Research Article
  • Citations15

Lambertian-based adversarial attacks on deep-learning-based underwater side-scan sonar image classification

  • Feb 08, 2023
  • Pattern Recognition
  • Qixiang Ma +2
  • Research Article
  • Citations21

Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples

  • Mar 15, 2024
  • ACM Transactions on Software Engineering and Methodology
  • Zhe Zhao +6
  • Conference Article
  • Citations10

Adversarial Image Attacks Using Multi-Sample and Most-Likely Ensemble Methods

  • Oct 12, 2020
  • Xia Du +1
  • Research Article
  • Citations256

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain

  • May 25, 2021
  • ACM Computing Surveys
  • Ishai Rosenberg +3
  • Conference Article
  • Citations1

Adversarial Attack Algorithm based on Saliency Detection

  • Mar 12, 2021
  • Sijie Liu +3
  • Research Article
  • Citations4

Towards Patch-Based Noise Compression for Adversarial Attack Against Transformer-Based Visual Tracking

  • Jan 01, 2026
  • IEEE Transactions on Information Forensics and Security
  • Peng Gao +6
  • Research Article
  • Citations6

Generating Imperceptible and Cross-Resolution Remote Sensing Adversarial Examples Based on Implicit Neural Representations

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yu Zhang +5
  • Research Article

Transfer-based Adversarial Attack with Rectified Adam and Color Invariance

  • Jan 01, 2022
  • International Journal of Software and Informatics
  • Jia Ding +1
  • Research Article
  • Citations11

Adversarial Attack and Reliable Defense Based on Frequency Domain Feature Enhancement for Automatic Modulation Classification

  • Jan 01, 2025
  • IEEE Transactions on Information Forensics and Security
  • Yongchao Meng +5
  • Research Article
  • Citations8

On-manifold adversarial attack based on latent space substitute model

  • May 24, 2022
  • Computers & Security
  • Chunkai Zhang +2
  • Research Article
  • Citations21

Adversarial robustness and attacks for multi-view deep models

  • Nov 12, 2020
  • Engineering Applications of Artificial Intelligence
  • Xuli Sun +1
  • Research Article
  • Citations83

POBA-GA: Perturbation optimized black-box adversarial attacks via genetic algorithm

  • Apr 30, 2019
  • Computers & Security
  • Jinyin Chen +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.