How to Pretrain for Steganalysis

Abstract

In this paper, we investigate the effect of pretraining CNNs on Ima-geNet on their performance when refined for steganalysis of digital images. In many cases, it seems that just 'seeing' a large number of images helps with the convergence of the network during the refinement no matter what the pretraining task is. To achieve the best performance, the pretraining task should be related to steganalysis, even if it is done on a completely mismatched cover and stego datasets. Furthermore, the pretraining does not need to be carried out for very long and can be done with limited computational resources. An additional advantage of the pretraining is that it is done on color images and can later be applied for steganalysis of color and grayscale images while still having on-par or better performance than detectors trained specifically for a given source. The refining process is also much faster than training the network from scratch. The most surprising part of the paper is that networks pretrained on JPEG images are a good starting point for spatial domain steganalysis as well.

Fighting the Reverse JPEG Compatibility Attack: Pick your Side

“…The second detector we use, in order to verify that our method does not introduce detectable artifacts in the pixel domain, is the JIN-SRNet [8] -SRNet [5] pre-trained on ImageNet embedded with J-UNIWARD. Since pre-training of both detectors is executed on color images, they expect three-channel inputs.…”

Analyzing the accuracy of detecting steganograms formed by adaptive steganographic methods when using artificial neural networks

“…Despite the emergence of the latest types of CNN for the tasks of DI stegoanalysis, the operational accuracy of steganography detectors based on them significantly depends on the presence of a priori data on the used steganographic method and statistical parameters of the examined images [26,27,33]. That predetermines the relevance of the task of devising high-precision methods for DI stegoanalysis, capable of ensuring high accuracy of steganogram detection under conditions of the limited a priori data on the used steganographic method and a significant variation in the parameters of the examined images while maintaining relatively low computational complexity of adjustment.…”

“…To tackle this issue, a number of methods were proposed aimed at using pre-configured CNN [33], an ensemble of several artificial neural networks [3,34], special types of layers of artificial neurons [30], and so on. These methods are aimed at overcoming only certain limitations of existing CNN for the tasks of DI stegoanalysis, in particular, increasing the accuracy of work on new image packages, reducing the computational complexity of SD configuration methods, etc.…”

Detector-Informed Batch Steganography and Pooled Steganalysis

“…EfN B4 and Xu2 were modied by removing the average pooling and strides from the rst two layers as described in [25]. All network detectors are pre-trained on ImageNet, SRNet was pre-trained on a binary task of steganalyzing J-UNIWARD [9] (the so-called JIN pre-training exactly as described in [3]), while the other networks were pre-trained on the ImageNet classication task. 5 Steganalysis training on HILL / MiPOD is done with relative payloads randomly drawn from the uniform distribution on the set of relative payloads P = {0.05, 0.1, 0.2, .…”