Bridging disorder and order in random lasers for cryptographic applications via deep learning

Zhijia Hu; Lianghao Qi; Shilong He; Yalan Li; Siqi Li; Bin Chen; Wenyu Du; Yan Kuai; Zhigang Cao; Min Wang; Kaiming Zhou; Lin Zhang; Qingchuan Guo; Weimin Ding; Chao Li; Kang Xie; Anderson S. L. Gomes; Benli Yu

doi:10.1038/s42005-026-02600-z

Bridging disorder and order in random lasers for cryptographic applications via deep learning

Zhijia Hu^*
, Lianghao Qi
, Shilong He
, Yalan Li
, Siqi Li^*
, Bin Chen
, Wenyu Du
, Yan Kuai
, Zhigang Cao
, Min Wang
, Kaiming Zhou
, Lin Zhang
, Qingchuan Guo
, Weimin Ding
, Chao Li
, Kang Xie
, Anderson S. L. Gomes^*
, Benli Yu

^*Corresponding author for this work

Anhui University
Peng Cheng Laboratory
Guangdong University of Technology
Universidade Federal de Pernambuco

Research output: Contribution to journal › Article › peer-review

Abstract

Random lasers rely on multiple scattering in disordered media to generate emission with complex spectral behavior. While their high-entropy output is valuable for random number generation, the inherent unpredictability has historically limited their utility in structured information processing. Here, we demonstrate the coexistence of spectral randomness and determinism within these systems. Using deep neural networks for multi-dimensional spectral analysis, we identify inter-modal correlations that permit partial recovery of spectral intensity components, despite temporal fluctuations. We then develop a key generation and distribution scheme utilizing the dual nature of random lasers: the disorder ensures cryptographic randomness, while the underlying order facilitates accurate key transmission. This work presents a framework for physical-layer security, suggesting potential applications in photonic-based cryptography and secure communications.

Original language	English
Article number	132
Number of pages	12
Journal	Communications Physics
Volume	9
Issue number	1
Early online date	15 Apr 2026
DOIs	https://doi.org/10.1038/s42005-026-02600-z
Publication status	E-pub ahead of print - 15 Apr 2026

Bibliographical note

Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

Access to Document

10.1038/s42005-026-02600-zLicence: CC BY 4.0

Bridging disorder and order in random lasers for cryptographic applications via deep learning
Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
Final published version, 4.16 MBLicence: CC BY 4.0

Cite this

Hu, Z., Qi, L., He, S., Li, Y., Li, S., Chen, B., Du, W., Kuai, Y., Cao, Z., Wang, M., Zhou, K., Zhang, L., Guo, Q., Ding, W., Li, C., Xie, K., Gomes, A. S. L., & Yu, B. (2026). Bridging disorder and order in random lasers for cryptographic applications via deep learning. Communications Physics, 9(1), Article 132. Advance online publication. https://doi.org/10.1038/s42005-026-02600-z

@article{e4731d1a661249bf9daabc453fd072a3,

title = "Bridging disorder and order in random lasers for cryptographic applications via deep learning",

abstract = "Random lasers rely on multiple scattering in disordered media to generate emission with complex spectral behavior. While their high-entropy output is valuable for random number generation, the inherent unpredictability has historically limited their utility in structured information processing. Here, we demonstrate the coexistence of spectral randomness and determinism within these systems. Using deep neural networks for multi-dimensional spectral analysis, we identify inter-modal correlations that permit partial recovery of spectral intensity components, despite temporal fluctuations. We then develop a key generation and distribution scheme utilizing the dual nature of random lasers: the disorder ensures cryptographic randomness, while the underlying order facilitates accurate key transmission. This work presents a framework for physical-layer security, suggesting potential applications in photonic-based cryptography and secure communications.",

author = "Zhijia Hu and Lianghao Qi and Shilong He and Yalan Li and Siqi Li and Bin Chen and Wenyu Du and Yan Kuai and Zhigang Cao and Min Wang and Kaiming Zhou and Lin Zhang and Qingchuan Guo and Weimin Ding and Chao Li and Kang Xie and Gomes, \{Anderson S. L.\} and Benli Yu",

note = "Copyright {\textcopyright} The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.",

year = "2026",

month = apr,

day = "15",

doi = "10.1038/s42005-026-02600-z",

language = "English",

volume = "9",

journal = "Communications Physics",

issn = "2399-3650",

publisher = "Springer",

number = "1",

}

TY - JOUR

T1 - Bridging disorder and order in random lasers for cryptographic applications via deep learning

AU - Hu, Zhijia

AU - Qi, Lianghao

AU - He, Shilong

AU - Li, Yalan

AU - Li, Siqi

AU - Chen, Bin

AU - Du, Wenyu

AU - Kuai, Yan

AU - Cao, Zhigang

AU - Wang, Min

AU - Zhou, Kaiming

AU - Zhang, Lin

AU - Guo, Qingchuan

AU - Ding, Weimin

AU - Li, Chao

AU - Xie, Kang

AU - Gomes, Anderson S. L.

AU - Yu, Benli

N1 - Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

PY - 2026/4/15

Y1 - 2026/4/15

N2 - Random lasers rely on multiple scattering in disordered media to generate emission with complex spectral behavior. While their high-entropy output is valuable for random number generation, the inherent unpredictability has historically limited their utility in structured information processing. Here, we demonstrate the coexistence of spectral randomness and determinism within these systems. Using deep neural networks for multi-dimensional spectral analysis, we identify inter-modal correlations that permit partial recovery of spectral intensity components, despite temporal fluctuations. We then develop a key generation and distribution scheme utilizing the dual nature of random lasers: the disorder ensures cryptographic randomness, while the underlying order facilitates accurate key transmission. This work presents a framework for physical-layer security, suggesting potential applications in photonic-based cryptography and secure communications.

AB - Random lasers rely on multiple scattering in disordered media to generate emission with complex spectral behavior. While their high-entropy output is valuable for random number generation, the inherent unpredictability has historically limited their utility in structured information processing. Here, we demonstrate the coexistence of spectral randomness and determinism within these systems. Using deep neural networks for multi-dimensional spectral analysis, we identify inter-modal correlations that permit partial recovery of spectral intensity components, despite temporal fluctuations. We then develop a key generation and distribution scheme utilizing the dual nature of random lasers: the disorder ensures cryptographic randomness, while the underlying order facilitates accurate key transmission. This work presents a framework for physical-layer security, suggesting potential applications in photonic-based cryptography and secure communications.

UR - https://www.nature.com/articles/s42005-026-02600-z

UR - https://www.scopus.com/pages/publications/105036152943

U2 - 10.1038/s42005-026-02600-z

DO - 10.1038/s42005-026-02600-z

M3 - Article

SN - 2399-3650

VL - 9

JO - Communications Physics

JF - Communications Physics

IS - 1

M1 - 132

ER -

Bridging disorder and order in random lasers for cryptographic applications via deep learning

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this