Study on the interaction between the cover source mismatch and texture complexity in steganalysis

Abstract

Cover source mismatch (CSM) occurs when a detection classifier for steganalysis trained on objects from one cover source is tested on another source. However, it is very hard to find the same sources as suspicious images in real-world applications. Therefore, the CSM is one of the biggest stumbling blocks to hinder current classifier based steganalysis methods from becoming practical. Meanwhile, the texture complexity (of digital images) also plays an important role in affecting the detection accuracy of steganalysis. Previous work seldom conduct research on the interaction between the two factors of the CSM and the texture complexity (TC). This paper studies the interaction between the two factors and explore certain factor related to cover source mismatch, aiming to improve the steganalysis accuracy in the case of CSM. We propose an effective method to measure the TC via image filtering, and use the two-way analysis of variance to study the interaction between the two factors. Both non-adaptive and adaptive steganography experiments are carried out with different levels of TC and CSM. The experimental results have shown that the interaction between the two factors affects the detection accuracy significantly.