Optimized Feature Selection for DDoS Attack Recognition and Mitigation in SD-VANETs

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Vehicular Ad-Hoc Networks (VANETs) are pivotal to the advancement of intelligent transportation systems (ITS), enhancing safety and efficiency on the road through secure communication networks. However, the integrity of these systems is severely threatened by Distributed Denial-of-Service (DDoS) attacks, which can disrupt the transmission of safety-critical messages and put lives at risk. This research paper focuses on developing robust detection methods and countermeasures to mitigate the impact of DDoS attacks in VANETs. Utilizing a combination of statistical analysis and machine learning techniques (i.e., Autoencoder with Long Short-Term Memory (LSTM), and Clustering with Classification), the study introduces innovative approaches for real-time anomaly detection and system resilience enhancement. Emulation results confirm the effectiveness of the proposed methods in identifying and countering DDoS threats, significantly improving (i.e., 94 percent anomaly detection rate) the security posture of a high mobility-aware ad hoc network. This research not only contributes to the ongoing efforts to secure VANETs against DDoS attacks but also lays the groundwork for more resilient intelligent transportation systems architectures.

Original languageEnglish
Article number395
JournalWorld Electric Vehicle Journal
Volume15
Issue number9
DOIs
StatePublished - Sep 2024

Keywords

  • cooperative decentralized intrusion detection system (CD-IDS)
  • Distributed Denial-of-Service (DDoS)
  • filtering mechanisms
  • network resilience
  • permissioned blockchain
  • real-time cooperative communication
  • Software Defined Vehicular Ad-Hoc Networks (SD-VANETs)
  • traffic analysis
  • trust management

Fingerprint

Dive into the research topics of 'Optimized Feature Selection for DDoS Attack Recognition and Mitigation in SD-VANETs'. Together they form a unique fingerprint.

Cite this