Few-shot Text Steganalysis Based on Attentional Meta-learner

Abstract

Text steganalysis is a technique to distinguish between steganographic text and normal text via statistical features. Current stateof-the-art text steganalysis models have two limitations. First, they need su cient amounts of labeled data for training. Second, they lack the generalization ability on di erent detection tasks. In this paper, we propose a meta-learning framework for text steganalysis in the few-shot scenario to ensure model fast-adaptation between tasks. A general feature extractor based on BERT is applied to extract universal features among tasks, and a meta-learner based on attentional Bi-LSTM is employed to learn task-speci c representations. A classi er trained on the support set calculates the prediction loss on the query set with a few samples to update the meta-learner. Extensive experiments show that our model can adapt fast among di erent steganalysis tasks through extremely few-shot samples, signi cantly improving detection performance compared with the state-of-the-art steganalysis models and other meta-learning methods. CCS CONCEPTS• Security and privacy → Human and societal aspects of security and privacy; • Computing methodologies → Natural language processing.