Enhancing JPEG Steganography using Iterative Adversarial Examples

TL;DR

This paper introduces an iterative adversarial example-based framework to improve JPEG steganography security by updating embedding costs to evade modern steganalytic CNN models.

Contribution

It proposes a novel iterative adversarial approach that enhances JPEG steganography security by adapting embedding costs against advanced CNN-based steganalysis.

Findings

Significant security improvement against GFR, SCA-GFR, and SRNet models.

Effective in reducing detectability of steganographic content.

Framework adaptable to different steganalytic models.

Abstract

Convolutional Neural Networks (CNN) based methods have significantly improved the performance of image steganalysis compared with conventional ones based on hand-crafted features. However, many existing literatures on computer vision have pointed out that those effective CNN-based methods can be easily fooled by adversarial examples. In this paper, we propose a novel steganography framework based on adversarial example in an iterative manner. The proposed framework first starts from an existing embedding cost, such as J-UNIWARD in this work, and then updates the cost iteratively based on adversarial examples derived from a series of steganalytic networks until achieving satisfactory results. We carefully analyze two important factors that would affect the security performance of the proposed framework, i.e. the percentage of selected gradients with larger amplitude and the adversarial intensity to modify embedding cost. The experimental results evaluated on three modern steganalytic models, including GFR, SCA-GFR and SRNet, show that the proposed framework is very promising to enhance the security performances of JPEG steganography.