Threats of Deep Learning Attacks to Chaos-Based Spread-Spectrum System

  • Hue Ta Thi Kim Hanoi University of Science and Technology
  • Dat Nguyen Thanh Hanoi University of Science and Technology
  • Hieu Hoang Duc Hanoi University of Science and Technology
  • Quyen Nguyen Xuan Hanoi University of Science and Technology

Abstract

Chaos-based spread-spectrum systems exploit chaotic carriers or sequences resembling random noise to transmit and recover information, often employing chaotic spectrum spreading as a form of physical-layer encryption. Representative spread-spectrum schemes, such as Chaotic CDMA and Differential Chaos Shift Keying (DCSK), have been shown to be highly sensitive to noise, parameter mismatches, and their reliance on obfuscation makes them vulnerable to sophisticated attacks. In this paper, we examine the susceptibility of chaos-based spread-spectrum schemes to modern deep learning techniques. By integrating Gramian Angular Field (GAF) encoding with the ResNet50 architecture, we demonstrate effective prediction and reconstruction of hidden chaotic key sequences, even under noisy and fading channel conditions. Experimental results confirm that digital communication systems employing chaotic spread-spectrum modulation can be systematically compromised by advanced deep learning methods, posing new challenges for enhancing their robustness and cryptographic reliability in practical applications.

Author Biographies

Hue Ta Thi Kim, Hanoi University of Science and Technology
Ta Thi Kim Hue received the Diploma of Engineer, Master and PhD degrees in Electronic Engineering and Telecommunication Technologies from Hanoi University of Science and Technology, Vietnam, in 2007, 2009, and 2016, respectively. From 2015 to 2016, she was an exchange PhD student at the Department of Electronics and Informatics, Vrije Universiteit Brussel, Belgium. She has served as a lecturer at the SET of HUST since 2012. She is (co-)author of over 20 international publications. She has been a program committee member for numerous conferences and workshops (ICCE 2016, 2018, ATC 2017, 2018). She regularly reviews papers for multiple journals, such as the Journal of Science and Technology and the Journal of Military Science and Technology Vietnam. She worked for almost 15 years as a researcher at the Signal Information Processing Laboratory, Hanoi University of Science and Technology. Her current interests include complex networks, cryptography, and physical security protocols for future internet.
Dat Nguyen Thanh, Hanoi University of Science and Technology
Nguyen Thanh Dat received the Bachelor's degree in Electronics and Telecommunications Engineering (Talented Program) from the School of Electrical and Electronic Engineering (SEEE), Hanoi University of Science and Technology (HUST), Vietnam, in 2026. His research interests include AI applications, deep learning, chaos-based communications, chaos theory, and AI security.
Hieu Hoang Duc, Hanoi University of Science and Technology
Hoang Duc Hieu received the Bachelor’s degree in Electronics and Telecommunications Engineering in 2024. He is currently pursuing the Master’s degree in Telecommunications Engineering. His research interests include wireless communications, chaos-based applications, signal processing, physical layer security, and artificial intelligence applications in communication systems.
Quyen Nguyen Xuan, Hanoi University of Science and Technology
Nguyen Xuan Quyen received the Diploma of Engineer, Master and PhD degrees in Electronics and Telecommunications in 2006, 2008 and 2013, respectively. He was an exchange PhD student at the Institute for Smart System Technologies, Alpen-Adria Klagenfurt University, Austria, during 2011-2012. During 2014-2015, he worked as a postdoctoral researcher at the Department of Computer Architecture, Polytechnic University of Catalonia (UPC BarcelonaTech), Spain. He was also an academic visitor at the Department of Electronic and Computer Engineering, University of Limerick, Ireland in 2015, at the School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, United Kingdom in 2016, and at the Department of Computer and Network Engineering, The University of Electro-Communications, Tokyo-Japan in 2017. From 2017 to current, he has been serving as a senior lecturer and associate professor at the School of Electrical and Electronic Engineering (SEEE), Hanoi University of Science and Technology (HUST), Vietnam. His main research interests are microwave design and implementation, chaos-based digital communications, physical layer security, and wireless communications.
Published
2026-05-13
Issue
Accepted articles
Section
REV-ECIT Special Issue
An author's submission implies that the manuscript has not been published previously, and is not currently submitted for publication elsewhere. Submission also implies that the Corresponding Author has consent of all authors (the Authors). Upon acceptance for publication transfer of copyright will be made to the Publisher of REV-JEC, who guarantees that full content of the published article is freely distributed on the Journal's website. The copyright transfer gives the Publisher of REV-JEC full authority to resolve any complaints of misuse or abuse (such as infringement or plagiarism) of the published article. The Authors have the freedom to redistribute and reuse the published article in any medium or format for any purpose, provided the original published article is properly cited. An article submission implies author agreement with this policy.