article · Cybersecurity
Digital media can be used to hide secret information, but automated steganalysis techniques can detect these alterations. While convolutional neural networks have improved detection over traditional machine learning methods, earlier models faced issues with training stability and classification accuracy. A newly developed convolutional neural network architecture addresses these limitations across three structured stages: pre-processing, feature extraction, and classification. Pre-processing uses spatial rich model filters to accentuate hidden noise patterns. Feature extraction combines depthwise separable convolutions with regular convolutions to capture local features while enhancing signal-to-noise ratios. Finally, multi-scale average pooling aggregates features across varying image sizes before fully connected layers generate class probabilities. Testing shows detection accuracy improvements of between 4.6 and 10.2 per cent over a recent benchmark scheme, alongside a reduction in training time of up to 30.81 per cent.
Steganalysis plays a vital role in identifying covert communications and illicit data concealed inside ordinary digital pictures. By increasing detection accuracy while lowering the time required to train deep learning models, this development helps cybersecurity analysts uncover hidden payloads more reliably and efficiently, even when handling images of varying dimensions.
The abstract describes early-stage, tested algorithmic research aimed at detecting concealed data in digital images. Potential users include digital media forensics teams, cybersecurity monitoring services, and law enforcement analysts seeking automated tools to identify illicit data transfer. While laboratory tests show enhanced accuracy and faster training, the abstract provides no evidence of deployment in operational security pipelines or commercial software products.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Hiding secret data in digital multimedia has been essential to protect the data. Nevertheless, attackers with a steganalysis technique may break them. Existing steganalysis methods have good results with conventional Machine Learning (ML) techniques; however, the introduction of Convolutional Neural Network (CNN), a deep learning paradigm, achieved better performance over the previously proposed ML-based techniques. Though the existing CNN-based approaches yield good results, they present performance issues in classification accuracy and stability in the network training phase. This research proposes a new method with a CNN architecture to improve the hidden data detection accuracy and the training phase stability in spatial domain images. The proposed method comprises three phases: pre-processing, feature extraction, and classification. Firstly, in the pre-processing phase, we use spatial rich model filters to enhance the noise within images altered by data hiding; secondly, in the feature extraction phase, we use two-dimensional depthwise separable convolutions to improve the signal-to-noise and regular convolutions to model local features; and finally, in the classification, we use multi-scale average pooling for local features aggregation and representability enhancement regardless of the input size variation, followed by three fully connected layers to form the final feature maps that we transform into class probabilities using the softmax function. The results identify an improvement in the accuracy of the considered recent scheme ranging between 4.6 and 10.2% with reduced training time up to 30.81%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s42400-023-00156-x
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
