# Hierarchical Graph Neural Network for Compressed Speech Steganalysis

arXiv: https://arxiv.org/abs/2507.21591 · HTML: https://mlsanity.com/paper/2507.21591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 72 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Federated Learning for Computer Vision](https://mlsanity.com/paper/2308.13558/) (2023)
- [Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions](https://mlsanity.com/paper/2308.04522/) (2023)
- [Compact Graph Architecture for Speech Emotion Recognition](https://mlsanity.com/paper/2008.02063/) (2020)
- [AI-Enabled System for Efficient and Effective Cyber Incident Detection and Response in Cloud Environments](https://mlsanity.com/paper/2404.05602/) (2024)
- [Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning](https://mlsanity.com/paper/2410.11463/) (2024)
- [Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows](https://mlsanity.com/paper/1902.01286/) (2019)
- [Graph Representation Learning for Spatial Image Steganalysis](https://mlsanity.com/paper/2110.00957/) (2021)
- [Hierarchical Representation Network for Steganalysis of QIM Steganography in Low-Bit-Rate Speech Signals](https://mlsanity.com/paper/1910.04433/) (2019)
- [Fast Steganalysis Method for VoIP Streams](https://mlsanity.com/paper/1910.14571/) (2019)
- [Subsequent embedding in targeted image steganalysis: Theoretical framework and practical applications](https://mlsanity.com/paper/2107.13862/) (2021)
- [FCEM: A Novel Fast Correlation Extract Model For Real Time Steganalysis of VoIP Stream via Multi-head Attention](https://mlsanity.com/paper/1911.00682/) (2019)
- [JPEG Steganalysis Based on Steganographic Feature Enhancement and Graph Attention Learning](https://mlsanity.com/paper/2302.02276/) (2023)
- [StegoHound: A Novel Multi-Approaches Method for Efficient and Effective Identification and Extraction of Digital Evidence Masked by Steganographic Techniques in WAV and MP3 Files](https://mlsanity.com/paper/2307.07293/) (2023)

## Abstract (arXiv)

Steganalysis methods based on deep learning (DL) often struggle with computational complexity and challenges in generalizing across different datasets. Incorporating a graph neural network (GNN) into steganalysis schemes enables the leveraging of relational data for improved detection accuracy and adaptability. This paper presents the first application of a Graph Neural Network (GNN), specifically the GraphSAGE architecture, for steganalysis of compressed voice over IP (VoIP) speech streams. The method involves straightforward graph construction from VoIP streams and employs GraphSAGE to capture hierarchical steganalysis information, including both fine grained details and high level patterns, thereby achieving high detection accuracy. Experimental results demonstrate that the developed approach performs well in uncovering quantization index modulation (QIM)-based steganographic patterns in VoIP signals. It achieves detection accuracy exceeding 98 percent even for short 0.5 second samples, and 95.17 percent accuracy under challenging conditions with low embedding rates, representing an improvement of 2.8 percent over the best performing state of the art methods. Furthermore, the model exhibits superior efficiency, with an average detection time as low as 0.016 seconds for 0.5-second samples an improvement of 0.003 seconds. This makes it efficient for online steganalysis tasks, providing a superior balance between detection accuracy and efficiency under the constraint of short samples with low embedding rates.