Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE Wireless Communications and Networking Conference

Learning Doppler-Resilient Keys via CNN-Based Channel Mapping for UAV Communications

Min-Wei Chen, Hai-Yan Huang, Yu‐Jia Chen, Chia-Hsiang Tseng

Published Apr 13, 2026• 0 citations
Publisher

Abstract

Physical layer key generation (PLKG) offers a lightweight and scalable approach to securing wireless communications by exploiting the reciprocity and randomness of the channel. However, in high-mobility scenarios such as unmanned aerial vehicle (UAV) communications, rapid channel variations and reduced coherence time undermine channel reciprocity, significantly degrading the reliability of PLKG. In this work, we propose a Doppler-resilient PLKG framework to improve key generation performance in dynamic wireless environments. We develop a convolutional neural network (CNN)-based model that learns to map the channel frequency response (CFR) observed at the ground control station (GCS) to the corresponding CFR at the UAV. By integrating Doppler frequency and CFR through a feature fusion layer, the framework adapts to varying mobility conditions and enables stable key generation across different Doppler scenarios. A unified model is trained on aggregated datasets to support robust performance without requiring Doppler-specific tuning. Simulation results demonstrate that the proposed method achieves superior key consistency and adaptability, significantly reducing the key disagreement rate (KDR) compared with existing deep learning-based approaches across a wide range of Doppler frequencies.

DOI
10.1109/wcnc65185.2026.11555515

Related papers

Stealth in Motion: A Doppler Shift-Induced Secret Key for Securing Air–Ground Communications

Qubeijian Wang, Shaojie Bai, Wen Yao Sun +4 more

The rapid evolution of unmanned aerial vehicles (UAVs) has positioned air-ground networks as vital infrastructures for diverse applications. However, the open channels of air-ground networks remain inherently vulnerable to persistent eavesdropping threats. While physical-layer key generation (PLKG) offers a lightweight security mechanism by leveraging channel reciprocity to extract shared secrets, the inherent mobility of UAVs introduces a paradoxical tradeoff. Increased channel randomness from dynamic flight patterns enhances security through entropy amplification but simultaneously disrupts channel reciprocity, leading to key mismatch between legitimate parties. Existing PLKG schemes struggle to maintain reliability in key generation due to static channel characteristics and synchronization overhead, limiting their practical deployment in air-ground networks. To resolve this conflict, we propose a Doppler shift key generation (DSKG) scheme that systematically regulates Doppler shifts through UAV trajectory design to derive secure keys. By formulating the problem as a Markov decision process, we develop a proximal policy optimization (PPO)-clip-based reinforcement learning algorithm to dynamically control UAV speed and steering angle, ensuring robust Doppler shift reciprocity while maximizing both key entropy and generation rate. Experimental results quantify the improvements of our scheme over benchmarks in maintaining high key unpredictability and generation efficiency. Furthermore, the analysis provides valuable insights into parameter impacts, confirming the practical viability of the DSKG scheme for securing air-ground communications.

IEEE Transactions on Information Forensics and Security•Jan 1, 2026•0 citations

Overcoming Channel Determinism in Maritime UAV Networks via RIS-Assisted PLKG with Deep Learning

Binglong Zhang, Desheng Wang, Lei Ding +1 more

Unmanned Aerial Vehicles (UAVs) have emerged as critical enablers for maritime Internet of Things (IoT) architectures due to their deployment flexibility. However, secure communication between UAVs and maritime nodes faces severe physical layer security challenges. Specifically, in maritime atmospheric ducting environments, radio waves exhibit high channel correlation and static determinism, which significantly limits the Secret Key Generation Rate (KGR) in traditional Physical Layer Key Generation (PLKG) schemes. To address these challenges, this paper proposes an AI-driven Reconfigurable Intelligent Surface (RIS)-synergized PLKG framework tailored for dynamic UAV networks. By deploying an RIS to construct a virtual Line-of-Sight (V-LoS) link, the proposed model achieves active channel fingerprint reshaping and entropy enhancement, effectively overcoming the deterministic bottleneck of highly correlated maritime channels even when the UAV operates in hovering or low-mobility states. Furthermore, a data-driven feature reconciliation mechanism is introduced, integrating Deep Neural Networks (DNNs) for non-linear feature extraction with the Fletcher-Reeves (FR) conjugate gradient method for phase optimization. This joint mechanism shifts the heavy computational burden of channel feature alignment to an offline phase, enabling ultra-low complexity online inference suitable for resourceconstrained nodes. Extensive simulation results demonstrate that the proposed framework significantly reduces online processing delay compared to traditional heuristic protocols. Notably, it maintains a near-flat normalized key disagreement rate well below the safety threshold, even at high UAV speeds of 120 km/h. The proposed scheme provides a high-entropy, lightweight, and theoretically secure solution for next-generation maritime UAV communications, successfully validating its efficacy in overcoming channel determinism in high-mobility scenarios.

International Conference on Computer Communication and Artificial Intelligence (CCAI)•May 1, 2026•0 citations

Enhancing Secret Key Generation for UAV Communications via Codeword Reconstruction

Yue Wang, Qinghe Du, Ning Shen +4 more

With the rapid advancement of unmanned aerial vehicle (UAV), ensuring the security of communication links among UAVs has become crucial. In this paper, we propose a novel physical layer key generation scheme based on channel codeword reconstruction. In UAV communications, the high mobility of aerial nodes leads to short channel coherence time, which together with noise causes inevitable channel estimation errors. These errors significantly degrades the performance of wireless channel-based key generation. Therefore, we propose a codeword construction algorithm that achieves a polarization characteristic, which effectively segregates reliable keys from unreliable ones. Compared to the existing quantization-based key generation scheme, our approach maximize the utilization of raw channel information and employ soft-decision decoding to generate key. Simulation results demonstrate that the proposed scheme reduces the key disagreement rate for legitimate users and increases the number of consistently generated keys. Furthermore, our method ensures a lower key consistency rate for eavesdropper, which guarantees system security.

IEEE Wireless Communications and Networking Conference Workshops (WCNCW)•Apr 13, 2026•1 citation

Enhancing Secret Key Generation for UAV Communications via Codeword Reconstruction

Yizhuo Wang, Qinghe Du, Ning Shen +3 more

With the rapid advancement of unmanned aerial vehicle (UAV), ensuring the security of communication links among UAVs has become crucial. In this paper, we propose a novel physical layer key generation scheme based on channel codeword reconstruction. In UAV communications, the high mobility of aerial nodes leads to short channel coherence time, which together with noise causes inevitable channel estimation errors. These errors significantly degrades the performance of wireless channel-based key generation. Therefore, we propose a codeword construction algorithm that achieves a polarization characteristic, which effectively segregates reliable keys from unreliable ones. Compared to the existing quantization-based key generation scheme, our approach maximize the utilization of raw channel information and employ soft-decision decoding to generate key. Simulation results demonstrate that the proposed scheme reduces the key disagreement rate for legitimate users and increases the number of consistently generated keys. Furthermore, our method ensures a lower key consistency rate for eavesdropper, which guarantees system security.

arXiv:2606.16644•Jun 15, 2026•0 citations

Physical-Layer Key Generation Efficient UAV Swarm Trajectory Planning

Xiaoyang Li, Tao Chen, Fangqi Wang +2 more

In order to enhance the secrecy transmission of unmanned aerial vehicle (UAV) swarm, a novel physical-layer key generation (PLKG) efficient UAV swarm trajectory planning method is proposed in this work. Different from the existing UAV trajectory planning methods that only focus on collision avoidance, energy saving and improving transmission quality, the proposed method incorporates the PLKG capability into the UAV trajectory design. Based on the findings of the fact that the wireless scattering experienced by UAV signals from different UAV trajectories are typically distinct, the channel randomness oriented PLKG behaves differently for various UAV trajectories. As a result, we propose to incorporate the PLKG metric into the UAV trajectory planning objectives, in order to improve the secrecy of UAV swarm transmissions. The theoretical derivation between UAV swarm PLKG metric and the wireless scattering entropy is obtained, and we propose a channel entropy knowledge sharing mechanism for UAV swarm to achieve PLKG efficient swarm trajectory planning. Simulation results show that the key generation performance can be largely improved in comparison to the traditional secrecy rate maximization oriented UAV swarm trajectory planning.

IEEE Transactions on Vehicular Technology•Jun 16, 2025•1 citation

A Low-Complexity Deep Learning Approach to Enhance Secret Key Generation for IoT Networks

Anas Alashqar, Ehsan Olyaei Torshizi, Raed Mesleh +1 more

This article presents a novel low-complexity deep learning model for physical-layer secret key generation (PSKG), specifically designed to enhance wireless security in the Internet of Things (IoT). PSKG typically generates cryptographic keys by exploiting the reciprocal nature of wireless channels; however, this reciprocity is frequently compromised in time-division duplex (TDD) systems due to hardware imperfections and noise, which significantly complicate the key generation process. To effectively address these challenges, the proposed deep neural network (DNN) is developed to efficiently learn and enhance reciprocity features, even in the presence of imperfect channel state information (CSI). Furthermore, the study introduces a DNN-based PSKG method that strategically leverages the phase of channel frequency responses for key extraction. The results conclusively demonstrate that the proposed model substantially reduces the key disagreement ratio (KDR) and enhances randomness, thus providing a robust and practical solution for securing wireless communications in IoT environments.

International Wireless Communications and Mobile Computing Conference (IWCMC)•May 12, 2025•1 citation
Physical layer key generation (PLKG) offers a lightweight and scalable approach to securing wireless communications by exploiting the reciprocity and randomness of the channel. However, in high-mobility scenarios such as unmanned aerial vehicle (UAV) communications, rapid channel variations and reduced coherence time undermine channel reciprocity, significantly degrading the reliability of PLKG. In this work, we propose a Doppler-resilient PLKG framework to improve key generation performance in dynamic wireless environments. We develop a convolutional neural network (CNN)-based model that learns to map the channel frequency response (CFR) observed at the ground control station (GCS) to the corresponding CFR at the UAV. By integrating Doppler frequency and CFR through a feature fusion layer, the framework adapts to varying mobility conditions and enables stable key generation across different Doppler scenarios. A unified model is trained on aggregated datasets to support robust performance without requiring Doppler-specific tuning. Simulation results demonstrate that the proposed method achieves superior key consistency and adaptability, significantly reducing the key disagreement rate (KDR) compared with existing deep learning-based approaches across a wide range of Doppler frequencies.
The rapid evolution of unmanned aerial vehicles (UAVs) has positioned air-ground networks as vital infrastructures for diverse applications. However, the open channels of air-ground networks remain inherently vulnerable to persistent eavesdropping threats. While physical-layer key generation (PLKG) offers a lightweight security mechanism by leveraging channel reciprocity to extract shared secrets, the inherent mobility of UAVs introduces a paradoxical tradeoff. Increased channel randomness from dynamic flight patterns enhances security through entropy amplification but simultaneously disrupts channel reciprocity, leading to key mismatch between legitimate parties. Existing PLKG schemes struggle to maintain reliability in key generation due to static channel characteristics and synchronization overhead, limiting their practical deployment in air-ground networks. To resolve this conflict, we propose a Doppler shift key generation (DSKG) scheme that systematically regulates Doppler shifts through UAV trajectory design to derive secure keys. By formulating the problem as a Markov decision process, we develop a proximal policy optimization (PPO)-clip-based reinforcement learning algorithm to dynamically control UAV speed and steering angle, ensuring robust Doppler shift reciprocity while maximizing both key entropy and generation rate. Experimental results quantify the improvements of our scheme over benchmarks in maintaining high key unpredictability and generation efficiency. Furthermore, the analysis provides valuable insights into parameter impacts, confirming the practical viability of the DSKG scheme for securing air-ground communications.
Unmanned Aerial Vehicles (UAVs) have emerged as critical enablers for maritime Internet of Things (IoT) architectures due to their deployment flexibility. However, secure communication between UAVs and maritime nodes faces severe physical layer security challenges. Specifically, in maritime atmospheric ducting environments, radio waves exhibit high channel correlation and static determinism, which significantly limits the Secret Key Generation Rate (KGR) in traditional Physical Layer Key Generation (PLKG) schemes. To address these challenges, this paper proposes an AI-driven Reconfigurable Intelligent Surface (RIS)-synergized PLKG framework tailored for dynamic UAV networks. By deploying an RIS to construct a virtual Line-of-Sight (V-LoS) link, the proposed model achieves active channel fingerprint reshaping and entropy enhancement, effectively overcoming the deterministic bottleneck of highly correlated maritime channels even when the UAV operates in hovering or low-mobility states. Furthermore, a data-driven feature reconciliation mechanism is introduced, integrating Deep Neural Networks (DNNs) for non-linear feature extraction with the Fletcher-Reeves (FR) conjugate gradient method for phase optimization. This joint mechanism shifts the heavy computational burden of channel feature alignment to an offline phase, enabling ultra-low complexity online inference suitable for resourceconstrained nodes. Extensive simulation results demonstrate that the proposed framework significantly reduces online processing delay compared to traditional heuristic protocols. Notably, it maintains a near-flat normalized key disagreement rate well below the safety threshold, even at high UAV speeds of 120 km/h. The proposed scheme provides a high-entropy, lightweight, and theoretically secure solution for next-generation maritime UAV communications, successfully validating its efficacy in overcoming channel determinism in high-mobility scenarios.
With the rapid advancement of unmanned aerial vehicle (UAV), ensuring the security of communication links among UAVs has become crucial. In this paper, we propose a novel physical layer key generation scheme based on channel codeword reconstruction. In UAV communications, the high mobility of aerial nodes leads to short channel coherence time, which together with noise causes inevitable channel estimation errors. These errors significantly degrades the performance of wireless channel-based key generation. Therefore, we propose a codeword construction algorithm that achieves a polarization characteristic, which effectively segregates reliable keys from unreliable ones. Compared to the existing quantization-based key generation scheme, our approach maximize the utilization of raw channel information and employ soft-decision decoding to generate key. Simulation results demonstrate that the proposed scheme reduces the key disagreement rate for legitimate users and increases the number of consistently generated keys. Furthermore, our method ensures a lower key consistency rate for eavesdropper, which guarantees system security.
With the rapid advancement of unmanned aerial vehicle (UAV), ensuring the security of communication links among UAVs has become crucial. In this paper, we propose a novel physical layer key generation scheme based on channel codeword reconstruction. In UAV communications, the high mobility of aerial nodes leads to short channel coherence time, which together with noise causes inevitable channel estimation errors. These errors significantly degrades the performance of wireless channel-based key generation. Therefore, we propose a codeword construction algorithm that achieves a polarization characteristic, which effectively segregates reliable keys from unreliable ones. Compared to the existing quantization-based key generation scheme, our approach maximize the utilization of raw channel information and employ soft-decision decoding to generate key. Simulation results demonstrate that the proposed scheme reduces the key disagreement rate for legitimate users and increases the number of consistently generated keys. Furthermore, our method ensures a lower key consistency rate for eavesdropper, which guarantees system security.
In order to enhance the secrecy transmission of unmanned aerial vehicle (UAV) swarm, a novel physical-layer key generation (PLKG) efficient UAV swarm trajectory planning method is proposed in this work. Different from the existing UAV trajectory planning methods that only focus on collision avoidance, energy saving and improving transmission quality, the proposed method incorporates the PLKG capability into the UAV trajectory design. Based on the findings of the fact that the wireless scattering experienced by UAV signals from different UAV trajectories are typically distinct, the channel randomness oriented PLKG behaves differently for various UAV trajectories. As a result, we propose to incorporate the PLKG metric into the UAV trajectory planning objectives, in order to improve the secrecy of UAV swarm transmissions. The theoretical derivation between UAV swarm PLKG metric and the wireless scattering entropy is obtained, and we propose a channel entropy knowledge sharing mechanism for UAV swarm to achieve PLKG efficient swarm trajectory planning. Simulation results show that the key generation performance can be largely improved in comparison to the traditional secrecy rate maximization oriented UAV swarm trajectory planning.
This article presents a novel low-complexity deep learning model for physical-layer secret key generation (PSKG), specifically designed to enhance wireless security in the Internet of Things (IoT). PSKG typically generates cryptographic keys by exploiting the reciprocal nature of wireless channels; however, this reciprocity is frequently compromised in time-division duplex (TDD) systems due to hardware imperfections and noise, which significantly complicate the key generation process. To effectively address these challenges, the proposed deep neural network (DNN) is developed to efficiently learn and enhance reciprocity features, even in the presence of imperfect channel state information (CSI). Furthermore, the study introduces a DNN-based PSKG method that strategically leverages the phase of channel frequency responses for key extraction. The results conclusively demonstrate that the proposed model substantially reduces the key disagreement ratio (KDR) and enhances randomness, thus providing a robust and practical solution for securing wireless communications in IoT environments.