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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Kaibo, Zhang, Zipei, Wei, Yukun, Zhang, TianXin, Yang, Zhongliang, Zhou, Linna
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909620799275008
author Huang, Kaibo
Zhang, Zipei
Wei, Yukun
Zhang, TianXin
Yang, Zhongliang
Zhou, Linna
author_facet Huang, Kaibo
Zhang, Zipei
Wei, Yukun
Zhang, TianXin
Yang, Zhongliang
Zhou, Linna
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
Huang, Kaibo
Zhang, Zipei
Wei, Yukun
Zhang, TianXin
Yang, Zhongliang
Zhou, Linna
Cryptography and Security
Artificial Intelligence
Computation and Language
68P30, 68T07
I.2.7
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.
title GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
topic Cryptography and Security
Artificial Intelligence
Computation and Language
68P30, 68T07
I.2.7
url https://arxiv.org/abs/2505.17085