Systematically Deconstructing APVD Steganography and its Payload with a Unified Deep Learning Paradigm

TL;DR

This paper introduces a deep learning model that detects APVD steganography and reconstructs hidden data with high accuracy, exposing vulnerabilities in adaptive steganography and aiding digital forensic efforts.

Contribution

It presents a novel CNN-based approach with attention mechanisms for simultaneous stego detection and payload recovery, advancing reverse steganalysis techniques.

Findings

Detection accuracy of 96.2% on benchmark datasets

Payload recovery up to 93.6% at low embedding densities

Inverse relationship between payload size and recovery accuracy

Abstract

In the era of digital communication, steganography allows covert embedding of data within media files. Adaptive Pixel Value Differencing (APVD) is a steganographic method valued for its high embedding capacity and invisibility, posing challenges for traditional steganalysis. This paper proposes a deep learning-based approach for detecting APVD steganography and performing reverse steganalysis, which reconstructs the hidden payload. We present a Convolutional Neural Network (CNN) with an attention mechanism and two output heads for simultaneous stego detection and payload recovery. Trained and validated on 10,000 images from the BOSSbase and UCID datasets, our model achieves a detection accuracy of 96.2 percent. It also reconstructs embedded payloads with up to 93.6 percent recovery at lower embedding densities. Results indicate a strong inverse relationship between payload size and recovery accuracy. This study reveals a vulnerability in adaptive steganography and provides a tool for digital forensic analysis, while encouraging reassessment of data security in the age of AI-driven techniques.