Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols
Abstract Vehicle-to-everything (V2X) communication has many benefits. It improves fuel efficiency, road safety, and traffic management. But it raises privacy and security concerns. These include the risk of cyberattacks and the loss of drivers’ personal data. Eavesdropping, data manipulation, and un...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82313-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559536079470592 |
|---|---|
| author | Thiruppathy Kesavan Venkatasamy Md. Jakir Hossen Gopi Ramasamy Nor Hidayati Binti Abdul Aziz |
| author_facet | Thiruppathy Kesavan Venkatasamy Md. Jakir Hossen Gopi Ramasamy Nor Hidayati Binti Abdul Aziz |
| author_sort | Thiruppathy Kesavan Venkatasamy |
| collection | DOAJ |
| description | Abstract Vehicle-to-everything (V2X) communication has many benefits. It improves fuel efficiency, road safety, and traffic management. But it raises privacy and security concerns. These include the risk of cyberattacks and the loss of drivers’ personal data. Eavesdropping, data manipulation, and unauthorized vehicle monitoring are major problems that need immediate attention. This paper proposes a new approach to intrusion detection in V2X communications. It uses machine learning-based cryptographic protocols for intrusion detection (ML-CPIDSs). The goal is to improve privacy and security in vehicular ad hoc networks (VANETs). The ML-CPIDS combines advanced cryptographic protocols with machine learning. It provides strong authentication, encryption, and real-time threat detection. Robust authentication and encryption techniques in modern cryptographic systems protect sensitive information. Using machine learning algorithms, it is feasible to identify and address security risks in real-time. The proposed technology solves key privacy and security issues. It has applications in many areas, including autonomous vehicle networks, urban traffic management, and vehicle communication systems. Extensive simulations show the ML-CPIDS works in different VANET environments. Privacy, security, and the ability to identify threats in real time are some of the areas that are evaluated in these simulations. The proposed ML-CPIDS approach outperforms current methods on several metrics. It has better privacy and authentication, lower latency, and stronger threat detection. It also improves the integrity and efficiency of V2X communications in VANET networks. |
| format | Article |
| id | doaj-art-3f17b835f05445e59b30b28dde6fbf92 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3f17b835f05445e59b30b28dde6fbf922025-01-05T12:23:53ZengNature PortfolioScientific Reports2045-23222024-12-0114111810.1038/s41598-024-82313-xIntrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocolsThiruppathy Kesavan Venkatasamy0Md. Jakir Hossen1Gopi Ramasamy2Nor Hidayati Binti Abdul Aziz3Faculty of Information Technology, Dhanalakshmi Srinivasan Engineering CollegeFaculty of Engineering and Technology, Multimedia UniversityFaculty of Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering CollegeFaculty of Engineering and Technology, Multimedia UniversityAbstract Vehicle-to-everything (V2X) communication has many benefits. It improves fuel efficiency, road safety, and traffic management. But it raises privacy and security concerns. These include the risk of cyberattacks and the loss of drivers’ personal data. Eavesdropping, data manipulation, and unauthorized vehicle monitoring are major problems that need immediate attention. This paper proposes a new approach to intrusion detection in V2X communications. It uses machine learning-based cryptographic protocols for intrusion detection (ML-CPIDSs). The goal is to improve privacy and security in vehicular ad hoc networks (VANETs). The ML-CPIDS combines advanced cryptographic protocols with machine learning. It provides strong authentication, encryption, and real-time threat detection. Robust authentication and encryption techniques in modern cryptographic systems protect sensitive information. Using machine learning algorithms, it is feasible to identify and address security risks in real-time. The proposed technology solves key privacy and security issues. It has applications in many areas, including autonomous vehicle networks, urban traffic management, and vehicle communication systems. Extensive simulations show the ML-CPIDS works in different VANET environments. Privacy, security, and the ability to identify threats in real time are some of the areas that are evaluated in these simulations. The proposed ML-CPIDS approach outperforms current methods on several metrics. It has better privacy and authentication, lower latency, and stronger threat detection. It also improves the integrity and efficiency of V2X communications in VANET networks.https://doi.org/10.1038/s41598-024-82313-xV2X communicationVehicular ad-hoc networksMachine learningIntrusion detection systemCryptography |
| spellingShingle | Thiruppathy Kesavan Venkatasamy Md. Jakir Hossen Gopi Ramasamy Nor Hidayati Binti Abdul Aziz Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols Scientific Reports V2X communication Vehicular ad-hoc networks Machine learning Intrusion detection system Cryptography |
| title | Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols |
| title_full | Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols |
| title_fullStr | Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols |
| title_full_unstemmed | Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols |
| title_short | Intrusion detection system for V2X communication in VANET networks using machine learning-based cryptographic protocols |
| title_sort | intrusion detection system for v2x communication in vanet networks using machine learning based cryptographic protocols |
| topic | V2X communication Vehicular ad-hoc networks Machine learning Intrusion detection system Cryptography |
| url | https://doi.org/10.1038/s41598-024-82313-x |
| work_keys_str_mv | AT thiruppathykesavanvenkatasamy intrusiondetectionsystemforv2xcommunicationinvanetnetworksusingmachinelearningbasedcryptographicprotocols AT mdjakirhossen intrusiondetectionsystemforv2xcommunicationinvanetnetworksusingmachinelearningbasedcryptographicprotocols AT gopiramasamy intrusiondetectionsystemforv2xcommunicationinvanetnetworksusingmachinelearningbasedcryptographicprotocols AT norhidayatibintiabdulaziz intrusiondetectionsystemforv2xcommunicationinvanetnetworksusingmachinelearningbasedcryptographicprotocols |