GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image Steganalysis
| Autor: | Burbano-Jacome Alejandro Buenaventura, Bravo-Ortiz Mario Alejandro, Isaza Gustavo, Ramos-Pollan Raul, Alzate-Grisales Jesus Alejandro, Tabares-Soto Reinel, Mora-Rubio Alejandro, Arias-Garzon Daniel, Arteaga-Arteaga Harold Brayan, Orozco-Arias Simon |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
General Computer Science
Computer science Feature extraction 0211 other engineering and technologies Convolutional neural network 02 engineering and technology Color depth 0202 electrical engineering electronic engineering information engineering General Materials Science steganalysis steganography Electrical and Electronic Engineering GBRAS-Net Steganalysis 021110 strategic defence & security studies Steganography business.industry Deep learning General Engineering deep learning Pattern recognition Filter (signal processing) 020201 artificial intelligence & image processing lcsh:Electrical engineering. Electronics. Nuclear engineering Artificial intelligence business lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 9, Pp 14340-14350 (2021) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2021.3052494 |
| Popis: | Advances in Deep Learning (DL) have provided alternative approaches to various complex problems, including the domain of spatial image steganalysis using Convolutional Neural Networks (CNN). Several CNN architectures have been developed in recent years, which have improved the detection accuracy of steganographic images. This work presents a novel CNN architecture which involves a preprocessing stage using filter banks to enhance steganographic noise, a feature extraction stage using depthwise and separable convolutional layers, and skip connections. Performance was evaluated using the BOSSbase 1.01 and BOWS 2 datasets with different experimental setups, including adaptive steganographic algorithms, namely WOW, S-UNIWARD, MiPOD, HILL and HUGO. Our results outperformed works published in the last few years in every experimental setting. This work improves classification accuracies on all algorithms and bits per pixel (bpp), reaching 80.3% on WOW with 0.2 bpp and 89.8% on WOW with 0.4 bpp, 73.6% and 87.1% on S-UNIWARD (0.2 and 0.4 bpp respectively), 68.3% and 81.4% on MiPOD (0.2 and 0.4 bpp), 68.5% and 81.9% on HILL (0.2 and 0.4 bpp), 74.6% and 84.5% on HUGO (0.2 and 0.4 bpp), using BOSSbase 1.01 test data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|