Sign in Subscribe
Machine learning

Machine Learning-based Intrusion Detection and Quantum Cryptography in Vehicular Networks

Strategic Insights

— 1 min read

Research conducted at the Cochin University of Science and Technology has developed a novel model for vehicle ad-hoc network security, leveraging machine learning and quantum cryptography to ensure secure communication between vehicles. This breakthrough addresses the persistent challenge of secure communication during vehicle-to-vehicle interactions. The proposed model, named Light Gradient-Boosting Machine Optimized Federated-Based Quantum Key Cryptography, has been demonstrated to be highly effective, achieving a packet delivery ratio of 96.9% and a detection accuracy of 98.82%. The research has significant implications for the automotive industry and the development of secure vehicular networks.

Key Takeaways:

  • The research proposes a novel model for vehicle ad-hoc network security, leveraging machine learning and quantum cryptography to ensure secure communication between vehicles.
  • The model, named Light Gradient-Boosting Machine Optimized Federated-Based Quantum Key Cryptography, has been demonstrated to be highly effective in detecting intrusions and ensuring secure communication.
  • The experimental evaluations conducted using the proposed model achieved a packet delivery ratio of 96.9%, energy consumption of 0.36 J, and detection accuracy of 98.82%.
  • The research has significant implications for the automotive industry and the development of secure vehicular networks.
  • The proposed model outperformed existing research articles in terms of efficiency and effectiveness.
  • The research has been peer-reviewed and published in the International Journal of Robust and Nonlinear Control.
  • The authors of the research include Abin John Joseph, V. J. Manoj, R. Nishanth, and R. Asaletha.

Statistics:

  • Packet delivery ratio: 96.9%
  • Energy consumption: 0.36 J
  • Detection accuracy: 98.82%
  • Precision: 98.5%
  • Sensitivity: 97.2%
  • F1-score: 97.85%
  • Throughput: 1568 bytes/s
  • Packet drop rate: 48%
  • Network lifetime: 320 time units
  • Fairness index: 1.24
  • Security rate: 98.2%

Sources:

  • International Journal of Robust and Nonlinear Control, 2025
  • Machine Learning-based Intrusion Detection and Quantum Cryptography In Vehicular Networks
  • Wiley, 111 River St, Hoboken 07030-5774, NJ, USA
  • Cochin University of Science and Technology, Dept. of Electrical and Communication Engineering, Cucek, Alleppey, Kerala, India
  • Abin John Joseph, V. J. Manoj, R. Nishanth, and R. Asaletha (authors)
  • NewsRx. Reports Outline Machine Learning Study Findings from Cochin University of Science and Technology (Machine Learning-based Intrusion Detection and Quantum Cryptography In Vehicular Networks). Information Technology Newsweekly. October 21, 2025; p 646.

Read more