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

TL;DR

GSDFuse is a comprehensive method that effectively detects linguistic steganography in social media by integrating multi-modal features, data augmentation, adaptive signal fusion, and discriminative embeddings, achieving state-of-the-art results.

Contribution

It introduces a holistic framework combining multiple techniques to overcome challenges in social media steganalysis, especially under data sparsity and complex dialogue conditions.

Findings

Achieves state-of-the-art detection accuracy on social media datasets.

Effectively handles data imbalance and steganographic sparsity.

Demonstrates robustness against sophisticated steganography methods.

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 https://github.com/NebulaEmmaZh/GSDFuse.