Abstract
Steganography is to hide secret information in a normal cover, so that the secret information cannot be detected. With the rapid development of steganography, it's more and more difficult to detect. Steganalysis is the counter of steganography. In order to improve the detection effect, more complex high-dimensional features are proposed for steganalysis. However, this also creates huge redundancy features, which in turn consume generous time. Feature selection is a technique that can effectively remove redundant features. In this paper, we propose a new blind image steganalysis algorithm to distinguish stego images from cover images using a nature-inspired feature selection method based on the binary bat algorithm(BBA). Meanwhile, SPAM and several classifiers have been used to improve the detection effect. Furthermore, we select the ideal feature subset using BBA from the original features and use the selected feature subset to train the several classifiers. The experimental results demonstrate that our proposed method can improve the detection effect and reduces the redundant features.
Highlights
With the development of information technologies, steganography has developed rapidly and many steganographic methods are proposed
STRUCTURE OF OUR APPROACH In this subsection, we present the whole structure of our proposed approach using binary bat algorithm together with the classifier to find the best performence of feature subset, as Fig. 1
In order to evaluate the performance in term of classification accuracyies and reduction of the features, our experiments are all compared to the original features of subtractive pixel adjacency model (SPAM) with the same classifiers
Summary
With the development of information technologies, steganography has developed rapidly and many steganographic methods are proposed. These methods embed secret information into the normal covers, such as images, audios, texts, and videos. As these behaviors do not change the visual effect of the covers, it’s hard to get alert. The methods embed the secret data into the spectrum space, such as Discrete Cosine Transform (DCT) [2] and Discrete Wavelet Transformation (DWT) [3]. The researchers can detect the stego images with simple statistical features. This promotes the further development of steganography. Some researchers further propose adaptive steganographic methods, such as Wavelet Obtained Weights
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call