[email protected] +91 9840521421 Scholarly Open Access, Peer-reviewed, Refereed Journal e-ISSN 2583-5300 Since 2022
  1. Home
  2. Archives
  3. 2026
  4. Vol. 5 Issue 3
  5. Article
Original Article

Real-Time Image Analysis System for Detecting and Monitoring Steganographic Attacks

Open Access Peer Reviewed

Authors

  • Nandeesh M Doggalli1
  • Meenakshi M V2
  • Sanjana G Patil3
  • Sheetal S Kulkarni4
  • Sneha P Patil5

1 Assistant Professor, Department of Information Science and Engineering, GM Institute of Technology, Davangere, Karnataka, India. 2 3 4 5 UG Scholars, Department of Information Science and Engineering, GM Institute of Technology, Davangere, Karnataka, India.

Article Information

DOI
No DOI
Published Online
September-December 2026
Pages
874-891
Article Type
Original Article
Check for updates
No DOI available for cross-reference

Abstract

View PDF

Steganography lets an attacker tuck secret data, or even a malicious payload, inside an ordinary-looking image. Someone who simply views or downloads that picture may end up exposed to covert communication, data leakage or hidden executable content, and nothing on screen will warn them. Spotting such content is hard. Common embedding methods, Least Significant Bit (LSB) substitution above all, alter pixel values only slightly, and most existing detectors are either simple offline statistical tools or deep-learning models that demand large datasets and heavy computation. This paper presents a Real-Time Image Analysis System for Detecting and Monitoring Steganographic Attacks: a lightweight client–server framework that watches images displayed in WhatsApp Web. A Manifest V3 Chrome extension keeps an eye on rendered images, retrieves their data through the Fetch API (or an HTML5 Canvas fallback) and passes them to a local Flask forensic API. The detection engine brings together LSB bit-stream inspection, Shannon entropy, chi-square pairs-of-values statistics, LSB bit-plane deviation, Gaussian residual-noise analysis, EXIF and optical-scene checks, and byte-level signature scanning for executable headers, script tokens and appended file containers. These indicators are fused into one composite score that maps to a SAFE, MEDIUM, HIGH or CRITICAL risk level. The extension communicates the level through green, amber and red borders, blurring, confirmation prompts and click interception. Every scan is written to a CSV history file and shown on a Streamlit Security Operations Center (SOC) dashboard. All 25 unit, integration, functional and system test cases passed. The prototype relies on interpretable heuristics rather than live deep-learning inference, and a labelled-dataset evaluation of accuracy, precision, recall and F1-score is the next planned step.

APC from ₹1200 + 18% GST

Peer-reviewed open access₹1200 Indian (₹1400 with DOI)$80 USD internationalpaid after acceptance Peer-reviewed open access₹1200 Indian$80 USD international ₹1200 Indian · $80 intl

  • CrossRef DOI
  • ISSN 2583-5300
  • Open Access
  • Peer Reviewed
  • Plagiarism Checked
  • Google Scholar
Contact Us Submit Paper