Steganalysis of Image with Adaptively Parametric Activation

TL;DR

This paper introduces an adaptive parametric activation module and enhanced filter constraints to improve the detection of hidden messages in images, achieving competitive results against state-of-the-art steganalysis methods.

Contribution

The paper proposes a novel adaptive activation function, filter constraints, and contrastive loss to better capture weak embedding signals in steganalysis.

Findings

Improved detection accuracy on BOSSbase images.

Enhanced residual diversity for richer signal extraction.

Competitive performance compared to existing methods.

Abstract

Steganalysis as a method to detect whether image contains se-cret message, is a crucial study avoiding the imperils from abus-ing steganography. The point of steganalysis is to detect the weak embedding signals which is hardly learned by convolution-al layer and easily suppressed. In this paper, to enhance embed-ding signals, we study the insufficiencies of activation function, filters and loss function from the aspects of reduce embedding signal loss and enhance embedding signal capture ability. Adap-tive Parametric Activation Module is designed to reserve nega-tive embedding signal. For embedding signal capture ability enhancement, we add constraints on the high-pass filters to im-prove residual diversity which enables the filters extracts rich embedding signals. Besides, a loss function based on contrastive learning is applied to overcome the limitations of cross-entropy loss by maximum inter-class distance. It helps the network make a distinction between embedding signals and semantic edges. We use images from BOSSbase 1.01 and make stegos by WOW and S-UNIWARD for experiments. Compared to state-of-the-art methods, our method has a competitive performance.