Using contrastive learning to improve the performance of steganalysis schemes
This work addresses the problem of enhancing steganalysis performance for security applications, but it is incremental as it builds on existing DNN methods with specific optimizations.
This paper tackled the problem of improving detection accuracy and generalization in steganalysis by proposing the Steganalysis Contrastive Framework (SCF) with a novel Steganalysis Contrastive Loss (StegCL), resulting in a maximum promotion of 2% in generalization and 3% in detection accuracy, and reducing training time to 10% of that using existing contrastive loss without decreasing accuracy.
To improve the detection accuracy and generalization of steganalysis, this paper proposes the Steganalysis Contrastive Framework (SCF) based on contrastive learning. The SCF improves the feature representation of steganalysis by maximizing the distance between features of samples of different categories and minimizing the distance between features of samples of the same category. To decrease the computing complexity of the contrastive loss in supervised learning, we design a novel Steganalysis Contrastive Loss (StegCL) based on the equivalence and transitivity of similarity. The StegCL eliminates the redundant computing in the existing contrastive loss. The experimental results show that the SCF improves the generalization and detection accuracy of existing steganalysis DNNs, and the maximum promotion is 2% and 3% respectively. Without decreasing the detection accuracy, the training time of using the StegCL is 10% of that of using the contrastive loss in supervised learning.