Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis

TL;DR

This paper introduces a domain adaptation approach for zero-shot text steganalysis using pseudo-labeling and a hybrid BERT-BiLSTM model to improve detection accuracy across different datasets without labeled target data.

Contribution

It proposes a novel pseudo-label based domain adaptation framework with a feature filtering mechanism and progressive sampling strategy for zero-shot text steganalysis.

Findings

Achieves high detection accuracy in zero-shot scenarios.

Outperforms existing zero-shot steganalysis methods.

Effective in handling domain shift without labeled target data.

Abstract

Currently, most methods for text steganalysis are based on deep neural networks (DNNs). However, in real-life scenarios, obtaining a sufficient amount of labeled stego-text for correctly training networks using a large number of parameters is often challenging and costly. Additionally, due to a phenomenon known as dataset bias or domain shift, recognition models trained on a large dataset exhibit poor generalization performance on novel datasets and tasks. Therefore, to address the issues of missing labeled data and inadequate model generalization in text steganalysis, this paper proposes a cross-domain stego-text analysis method (PDTS) based on pseudo-labeling and domain adaptation (unsupervised learning). Specifically, we propose a model architecture combining pre-trained BERT with a single-layer Bi-LSTM to learn and extract generic features across tasks and generate task-specific representations. Considering the differential contributions of different features to steganalysis, we further design a feature filtering mechanism to achieve selective feature propagation, thereby enhancing classification performance. We train the model using labeled source domain data and adapt it to target domain data distribution using pseudo-labels for unlabeled target domain data through self-training. In the label estimation step, instead of using a static sampling strategy, we propose a progressive sampling strategy to gradually increase the number of selected pseudo-label candidates. Experimental results demonstrate that our method performs well in zero-shot text steganalysis tasks, achieving high detection accuracy even in the absence of labeled data in the target domain, and outperforms current zero-shot text steganalysis methods.