Real-world actor-based image steganalysis via classifier inconsistency detection

TL;DR

This paper introduces a robust actor-based image steganalysis method that detects guilty actors and handles source mismatch issues using classifier inconsistency detection, neural networks, and gradient boosting, achieving over 80% accuracy.

Contribution

The paper presents a novel approach combining DCI prediction, EfficientNet, and Gradient Boosting to effectively address CSM in real-world steganalysis scenarios.

Findings

Achieves over 80% accuracy in high CSM scenarios

Outperforms baseline methods in detecting guilty actors

Remains reliable under diverse source mismatch conditions

Abstract

In this paper, we propose a robust method for detecting guilty actors in image steganography while effectively addressing the Cover Source Mismatch (CSM) problem, which arises when classifying images from one source using a classifier trained on images from another source. Designed for an actor-based scenario, our method combines the use of Detection of Classifier Inconsistencies (DCI) prediction with EfficientNet neural networks for feature extraction, and a Gradient Boosting Machine for the final classification. The proposed approach successfully determines whether an actor is innocent or guilty, or if they should be discarded due to excessive CSM. We show that the method remains reliable even in scenarios with high CSM, consistently achieving accuracy above 80% and outperforming the baseline method. This novel approach contributes to the field of steganalysis by offering a practical and efficient solution for handling CSM and detecting guilty actors in real-world applications.