Image Steganography based on Iteratively Adversarial Samples of A Synchronized-directions Sub-image

TL;DR

This paper introduces ITE-SYN, a novel steganography method that uses iterative adversarial perturbations and synchronized modification directions to improve security against both traditional and CNN-based steganalysis.

Contribution

The paper presents a new steganography scheme combining synchronized modification directions with iterative adversarial perturbations to enhance security against CNN and feature-based steganalysis.

Findings

Effectively counters CNN-based steganalysis.

Enhances security against feature-based classifiers.

Achieves high fooling rate for target CNN classifiers.

Abstract

Nowadays a steganography has to face challenges of both feature based staganalysis and convolutional neural network (CNN) based steganalysis. In this paper, we present a novel steganography scheme denoted as ITE-SYN (based on ITEratively adversarial perturbations onto a SYNchronized-directions sub-image), by which security data is embedded with synchronizing modification directions to enhance security and then iteratively increased perturbations are added onto a sub-image to reduce loss with cover class label of the target CNN classifier. Firstly an exist steganographic function is employed to compute initial costs. Then the cover image is decomposed into some non-overlapped sub-images. After each sub-image is embedded, costs will be adjusted following clustering modification directions profile. And then the next sub-image will be embedded with adjusted costs until all secret data has been embedded. If the target CNN classifier does not discriminate the stego image as a cover image, based on adjusted costs, we change costs with adversarial manners according to signs of gradients back-propagated from the CNN classifier. And then a sub-image is chosen to be re-embedded with changed costs. Adversarial intensity will be iteratively increased until the adversarial stego image can fool the target CNN classifier. Experiments demonstrate that the proposed method effectively enhances security to counter both conventional feature-based classifiers and CNN classifiers, even other non-target CNN classifiers.