Convolutional Neural Network to Detect the Secret Data in the Spatial Domain Images
Bibliographic record
Abstract
Advancements in Deep Learning (DL) have led to innovative approaches to address complex issues, notably steganalysis concerning spatial domain images.Steganalysis is a counter art of steganography that aims to detect the presence of possible hidden data in the pixels of an image.Based on the DL logic, Convolutional Neural Networks (CNNs) have been instrumental in this domain.Over the past years, several CNN architectures have emerged, elevating the accuracy in detecting the images hosting the steganographically hidden data in images.However, existing CNN models face problems associated with limitations in the perceptibility of low payload capacities and less-than-optimal processes for feature learning.This study introduces a novel CNN architecture to enhance the steganalysis process and improve the accuracy of secret data detection for spatial domain images.In the proposed method, the key contributions to CNN development include the utilization of mixed pooling, which combines different pool sizes to enhance the network's ability to capture deeper and multiple shades, thereby providing flexibility in feature extraction.Additionally, depth steganalysis and separable convolution address kernel neglect in channel and residual spatial correlation.Integrating LeakyReLu is proposed to mitigate weak slopes and enhance network convergence.Experimental results demonstrate that employing the proposed CNN architecture improves steganalysis outcomes.It is important to highlight that the findings reveal an accurate improvement of up to 10.2% over the recently considered schemes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".