Intelligent detection of adversaries in quantum key distribution-secured IoT networks using machine learning techniques

Dipanwita Debnath, Karri Manoz Kumar Reddy, Saka Satya Sudha, Anuradha Konidena, Vuppuloori Ravi Sekhara Reddy, Nallathambi Srija

Abstract


The increasing deployment of internet of things (IoT) devices in beyond-fifth-generation (B5G) and sixth-generation (6G) networks introduces significant security challenges due to limited computational and energy resources. Quantum key distribution (QKD) enables secure key establishment; however, malicious interference can compromise key generation and disrupt communication. This study aims to develop a machine learning (ML)-based framework for detecting adversarial interference using final quantum key length without interrupting QKD operation. A hierarchical architecture is proposed, assigning QKD and ML processing to capable IoT controllers and servers while maintaining lightweight sensor operations. A dataset containing 20,000 simulated QKD key-length samples, representing attack-free and attack-affected scenarios, is used to train and evaluate artificial neural network (ANN) and long short-term memory (LSTM) models. Experimental results demonstrate detection performance close to 99%, with ANN achieving substantially lower computational cost than LSTM. The framework is further considered for railway IoT monitoring, integrating fiber-optic QKD links between controllers and a control center with encrypted wireless sensor communication. The findings highlight the potential of final-key-length-based learning for lightweight, non-intrusive attack detection, while identifying synthetic data and single-feature learning as limitations requiring further validation.

Keywords


Attacker detection; Deep learning; Internet of things; Machine learning; Quantum key distribution; Railway systems

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v15i6.12530

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Statistics

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191 , e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) .