Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Performance Evaluation of zk-SNARK Protocols for Privacy-Preserving Sensor Data Verification: A Systematic Benchmarking Study.

Sensors (Basel, Switzerland)·2026
Same author

Security Audit of IoT Device Networks: A Reproducible Machine Learning Framework for Threat Detection and Performance Benchmarking.

Sensors (Basel, Switzerland)·2025
Same author

Model of an Open-Source MicroPython Library for GSM NB-IoT.

Sensors (Basel, Switzerland)·2025
Same author

Combined Pseudo-Random Sequence Generator for Cybersecurity.

Sensors (Basel, Switzerland)·2022
Same author

Optimization of a Simulated Annealing Algorithm for S-Boxes Generating.

Sensors (Basel, Switzerland)·2022
Same author

A Wavelet-Based Steganographic Method for Text Hiding in an Audio Signal.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

466

Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image

Oleksandr Kuznetsov1, Emanuele Frontoni2, Kyrylo Chernov3

  • 1Department of Theoretical and Applied Sciences, eCampus University, Via Isimbardi 10, 22060 Novedrate, Italy.

Sensors (Basel, Switzerland)
|December 17, 2024
PubMed
Summary

This study fine-tuned an AI model (SRNet) for detecting Spread Spectrum Image Steganography (SSIS), improving its accuracy on this novel technique. The research highlights the need for balanced AI model adaptation in image steganalysis.

Keywords:
convolutional neural networksfine-tuningimage steganography detectionspread spectrum image steganographysteganalysis models

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Related Experiment Videos

Last Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

466
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Cybersecurity

Background:

  • Image steganography poses a significant threat in digital security.
  • Existing steganalysis models may struggle with novel steganography techniques.
  • Convolutional Neural Networks (CNNs) show promise in detecting hidden data within images.

Purpose of the Study:

  • To evaluate the effectiveness of the SRNet model in detecting various image steganography techniques.
  • To improve SRNet's performance on Spread Spectrum Image Steganography (SSIS).
  • To investigate the trade-offs in AI model adaptation for steganalysis.

Main Methods:

  • Evaluated SRNet against WOW, HILL, S-UNIWARD, and SSIS.
  • Fine-tuned the SRNet model using SSIS-specific datasets.
  • Assessed performance changes post-fine-tuning across all tested steganography methods.

Main Results:

  • SRNet showed lower initial performance on SSIS detection.
  • Fine-tuning significantly improved SSIS detection accuracy.
  • A minor decrease in performance was observed for other steganography techniques after fine-tuning.

Conclusions:

  • AI-based steganalysis models like SRNet are adaptable and effective.
  • Careful balancing is required during model adaptation to maintain broad effectiveness.
  • Future research should explore multi-task learning and other ML techniques for enhanced steganalysis robustness.