Reliable Digital Image Authentication Using DNPLSB based Watermarking for Tamper Detection in Facial Images
Bibliographic record
Abstract
The increasing growth of digital images has become significant in the areas of healthcare, real-time governance, and social media activities to validate identity to offer services without any inconvenience. However, the rapid advancement of artificial intelligence and security-related concepts has led to an increase in real-time security attacks, such as deepfakes on digital images. Advanced technologies have been used by attackers to exploit sensitive data, necessitating the proposal of novel approaches to counter them. Numerous studies have evaluated tamper detection using watermarking techniques such as LSB, DCT, DWT, correlation-based methods, and hybrid approaches. The drawbacks of these existing techniques include low embedding density, memory inefficiency, and insufficient integrity checks, which impact tamper detection efficiency. To address these limitations, a novel watermarking technique is proposed that uses a Multi-task Cascaded Convolutional Neural Network (MTCNN) and a Penultimate Least Significant Bit (PLSB) approach to secure digital human images against unlawful activities such as deep fakes and tampering. The proposed framework outperforms existing methodologies in key performance metrics, including SVD-DWT, DCT, DNN, PB-DMFB, and PCA-DCT, achieving a 2 % increase in SSIM, a 12 % enhancement in PSNR, and a 4 % reduction in MSE, indicating superior quality of the watermarked image and enhanced resistance to manipulation and tampering.
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 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".