GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis

ACL ARR 2025 May Submission2966 Authors

Abstract: The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. Steganalysis is profoundly hindered by the challenge of identifying subtle cognitive inconsistencies arising from textual fragmentation and complex dialogue structures, and the difficulty in achieving robust aggregation of multi-dimensional weak signals, especially given extreme steganographic sparsity and sophisticated steganography. These core detection difficulties are compounded by significant data imbalance. This paper introduces GSDFuse, a novel method designed to systematically overcome these obstacles. GSDFuse employs a holistic approach, synergistically integrating hierarchical multi-modal feature engineering to capture diverse signals, strategic data augmentation to address sparsity, adaptive evidence fusion to intelligently aggregate weak signals, and discriminative embedding learning to enhance sensitivity to subtle inconsistencies. Experiments on social media datasets demonstrate GSDFuse's state-of-the-art (SOTA) performance in identifying sophisticated steganography within complex dialogue environments. The source code for GSDFuse is available at \url{https://anonymous.4open.science/r/GSDFuse-B1E7}.

Paper Type: Long

Research Area: Machine Learning for NLP

Research Area Keywords: NLP Applications, Machine Learning for NLP, Computational Social Science and Cultural Analytics

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Data analysis

Languages Studied: Chinese, English

Keywords: NLP Applications, Machine Learning for NLP, Computational Social Science and Cultural Analytics

Submission Number: 2966