CoChat
Sign Up
Cited by 1Chaos-based Image/Signal EncryptionComputer Science and EngineeringAdvanced Steganography and Watermarking Techniques

The DOI matches its Crossref record; the references it cites are not checked yet.

LSTM-driven chaotic keystream generator for robust medical image encryption

Open access
Niharika, Raavi, Ponnambalam, Mathivanan, Ponnambalam, Maran, Ghazalah, Sarah Abu, Awadelkarim, Awad M., Hong, Deukjo·2026·Scientific Reports
DOI 10.1038/s41598-026-49290-9
Open this paper in CoChat — free accountOpen PDF

Abstract

Medical image transmission and storage must be secure due to the rapid growth of digital healthcare systems and telemedicine. Medical images have high data volumes and strong pixel correlations, making conventional encryption algorithms inefficient or computationally expensive. Chaos-based encryption methods are popular due to their sensitivity to initial conditions and strong randomness, but finite precision limits key spaces and short periodicity in chaotic maps. A novel hybrid image encryption scheme is proposed that integrates long short-term memory (LSTM) networks with classical chaotic maps to generate adaptive keystreams using a hash float-seeded chaotic map and statistical features. The chaotic maps provide nonlinearity and high key sensitivity, while the LSTM extends the randomness, eliminates periodicity, and expands the key space to test its robustness. Three variants of the proposed model were experimented with: LSTM + Logistic, LSTM + sine map, and LSTM + Chebyshev map. Results demonstrate that all 3 models achieve strong encryption performance, but LSTM + Logistic map outperforms the other two in terms of randomness quality, noise, and crop attacks. The proposed model achieves 99.62% of NPCR, 39.59% of UACI, and 7.975 of entropy. Compared with conventional chaos methods and GAN encryption schemes, the proposed method provides high security, lightweight computation, and practical deployment.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-026-49290-9

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists haven’t been fetched yet

Cited by 1

Research works printed but not linked: 26

  1. Ahmed, S. T., Hammood, D. A., Chisab, R. F., Al-Naji, A. & Chahl, J. Medical image encryption: A comprehensive review. Computers 12(8), 160. https://doi.org/10.3390/computers12080160 (2023). · DOI
  2. Umar, T., Nadeem, M. & Anwer, F. Chaos based image encryption scheme to secure sensitive multimedia content in cloud storage. Expert Syst. Appl. 257, 125050. https://doi.org/10.1016/j.eswa.2024.125050 (2024). · DOI
  3. Kumar, B. S. & Revathi, R. An efficient image encryption algorithm using a discrete memory-based logistic map with deep neural network. J. Eng. Appl. Sci. 71, 41. https://doi.org/10.1186/s44147-023-00349-8 (2024). · DOI
  4. Panwar, K. et al. Encipher GAN: An end-to-end color image encryption system using a deep generative model. Systems 11(1), 36. https://doi.org/10.3390/systems11010036 (2023). · DOI
  5. Priyanka, P., Baranwal, N., Singh, K. N. & Singh, A. K. Using chaos to encrypt images with reconstruction through deep learning model for smart healthcare. Comput. Electr. Eng. 114, 109089. https://doi.org/10.1016/j.compeleceng.2024.109089 (2024). · DOI
  6. Long, B. et al. A novel medical image encryption scheme based on deep learning feature encoding and decoding. IEEE Access 12, 38382–38398 (2024). · DOI
  7. Maung Maung, A. P., Echizen, I. & Kiya, H. On the security of learnable image encryption for privacy-preserving deep learning. IEEE Access 12, 126415–126425. https://doi.org/10.1109/ACCESS.2024.3454199 (2024). · DOI
  8. Tiwari, A., Diwan, P., Diwan, T. D., Miroslav, M. & Samal, S. P. A compressed image encryption algorithm leveraging optimized 3D chaotic maps for secure image communication. Sci. Rep. 15, 1–15. https://doi.org/10.1038/s41598-025-95995-8 (2025). · DOI
  9. Kumar, M., Chivukula, A. S. & Barua, G. Deep learning-based encryption scheme for medical images using DCGAN and virtual planet domain. Sci. Rep. 15, 1–35. https://doi.org/10.1038/s41598-024-84186-6 (2025). · DOI
  10. Abirami, R. & Malathy, C. Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking. Automatika 66(2), 173–187. https://doi.org/10.1080/00051144.2025.2460877 (2025). · DOI
  11. Alsafyani, M., Alhomayani, F., Alsuwat, H. & Alsuwat, E. Face image encryption based on feature with optimization using secure crypto general adversarial neural network and optical chaotic map. Sensors 23(3), 1415. https://doi.org/10.3390/s23031415 (2023). · DOI
  12. Feng, L., Du, J. & Fu, C. Digital image encryption algorithm based on double chaotic map and LSTM. Comput. Mater. Contin. 77(2), 1645–1662. https://doi.org/10.32604/cmc.2023.042630 (2023). · DOI
  13. Kumar, D. A. K. et al. Role of machine learning in enhancing image encryption techniques for cybersecurity. Int. J. Intell. Syst. Appl. Eng. (IJISAE) 12(21s), 3904–3911 (2024).
  14. Huang, X., Dong, Y., Ye, G., Yap, W.-S. & Goi, B.-M. Visually meaningful image encryption algorithm based on digital signature. Digit. Commun. Netw. 9, 159–165. https://doi.org/10.1016/j.dcan.2022.04.028 (2023). · DOI
  15. Benaissi, S., Chikouche, N. & Hamza, R. A novel image encryption algorithm based on hybrid chaotic maps using a key image. Optik 272, 170316. https://doi.org/10.1016/j.ijleo.2022.170316 (2023). · DOI
  16. Liu, B. et al. Semantically enhanced selective image encryption scheme with parallel computing. Expert Syst. Appl. 279, 127404 (2025). · DOI
  17. Nickparvar, M. Brain Tumor MRI Dataset. (Kaggle, 2021). https://doi.org/10.34740/kaggle/dsv/2645886 · DOI
  18. Mayora-Cebollero, C., Mayora-Cebollero, A., Lozano, Á. & Barrio, R. Full Lyapunov exponents spectrum with deep learning from single-variable time series. Phys. D 472, 134510. https://doi.org/10.1016/j.physd.2024.134510 (2025). · DOI
  19. Zhu, J., Min, F., Yang, S. & Shi, W. Evolution of pitchfork bifurcation in a tabu learning neuron model and its application in image encryption. Chaos. Solitons. Fractals. 182, 114860. https://doi.org/10.1016/j.chaos.2024.114860 (2024). · DOI
  20. Liang, Q. & Zhu, C. A new one-dimensional chaotic map for image encryption scheme based on random DNA coding. Opt. Laser Technol. 160, 109033. https://doi.org/10.1016/j.optlastec.2022.109033 (2023). · DOI
  21. Li, S., Li, M., Li, Q. & Lv, Y. Hyperchaotic image encryption system based on deep learning LSTM. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 14(11), 338–347 (2023).
  22. Winarno, E., Nugroho, K., Adi, P. W. & Setiadi, D. R. I. M. Combined interleaved pattern to improve confusion-diffusion image encryption based on hyperchaotic system. IEEE Access 11, 69005–69023. https://doi.org/10.1109/ACCESS.2023.3285481 (2023). · DOI
  23. Liu, H., Liu, J. & Ma, C. Constructing dynamic strong S-Box using 3D chaotic map and application to image encryption. Multimed. Tools Appl. 82(16), 23899–23914 (2023). · DOI
  24. Tsai, M.-J., Lin, P.-Y. & Lee, M.-E. Adversarial attacks on medical image classification. Cancers 15(17), 4228. https://doi.org/10.3390/cancers15174228 (2023). · DOI
  25. Liu, H., Kadir, A. & Xu, C. Cryptanalysis and constructing S-Box based on chaotic map and backtracking. Appl. Math. Comput. 376, 125153 (2020).
  26. Song, W. et al. Batch image encryption using cross image permutation and diffusion. J. Inf. Secur. Appl. 80, 103686 (2024).

Metadata

Authors
Niharika, R., Ponnambalam, M., Ponnambalam, M., Ghazalah, S. A., Awadelkarim, A. M., & Hong, D.
Affiliations
  • Amrita Vishwa Vidyapeetham (IN)
  • King Khalid University (SA)
  • University of Tabuk (SA)
  • Jeonbuk National University (KR)
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2026-04-24
Volume
16
Issue
1
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-026-49290-9
OpenAlex
W7155504347
Cited by
1
References
0
Citations by year
2026: 1
FWCI
2.81
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Amrita Vishwa Vidyapeetham, Chennai
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
  • Physical Sciences › Computer Science › Artificial Intelligence › Computer Science and Engineering
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
Keywords
medical image encryption, chaos-based image encryption, long short-term memory networks, keystream generation, chaotic maps, logistic map, sine map, Chebyshev map, key space expansion, NPCR and UACI, telemedicine security
MeSH terms
Long Short Term Memory, Algorithms, Diagnostic Imaging, Humans, Image Processing, Computer-Assisted, Computer Security, Nonlinear Dynamics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: LSTM-driven chaotic keystream generator for robust medical image encryption. https://app.cochat.ai/papers/10.1038/s41598-026-49290-9
The paper
Niharika, R., Ponnambalam, M., Ponnambalam, M., Ghazalah, S. A., Awadelkarim, A. M., & Hong, D. (2026). LSTM-driven chaotic keystream generator for robust medical image encryption. Scientific Reports. https://doi.org/10.1038/s41598-026-49290-9