Enhancing Medical Image Security with FPGA-Accelerated LED Cryptography and LSB Watermarking
Bibliographic record
Abstract
In telemedicine, the safeguarding of medical images is important, necessitating systems that uphold patient privacy, ensure image integrity, and verify authenticity.Addressing the challenge of processing time disparities in existing algorithms, this study introduces a novel field-programmable gate array (FPGA)-based crypto-watermarking system for medical image applications.The system integrates a least significant bit (LSB) watermarking technique with the Lightweight Encryption Device (LED) cryptography algorithm.The LSB technique, known for its minimal impact on image quality, is utilized to embed a concealed message, subsequently encrypted by the LED algorithm for enhanced security.Traditional software implementations of such algorithms have been hampered by significant processing delays, with times ranging up to 34 seconds for smaller images and extending to 30 minutes for larger ones.The predominant factor in these delays, the encryption/decryption process, occupies 98% of the total processing time.To address this, the LED algorithm has been accelerated using Vitis High-Level Synthesis (HLS) for hardware implementation, effectively reducing time to market.The proposed architecture, subjected to rigorous examination, testing, and evaluation, demonstrates superior performance in throughput and processing speed compared to previous works.An extensive range of digital images was employed to assess the coprocessor's efficacy.The results reveal an average Peak Signal-to-Noise Ratio (PSNR) of 86.98 dB, indicating superior imperceptibility without attacks when compared to earlier studies.Furthermore, under various attack scenarios, the system maintains high imperceptibility, with an average PSNR of 53.68 dB, surpassing previous methods in robustness.Comparative tests confirm that the proposed FPGA-based crypto watermarking outstrips Real-Time Logic (RTL) implementations, achieving a PSNR above 82 dB.This indicates a marked improvement in imperceptibility relative to prior research.Additionally, the system boasts a throughput of 449.35 Mbps and a speed enhancement of 77% over traditional software implementations, underscoring its effectiveness in the secure processing of medical images.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".