DDoS Mitigation in SDN-Enabled VANET using Intelligent Traffic Control -- 2
Budget: ₹1,500 – ₹12,500 INR
Project Overview
Designed and implemented an intelligent DDoS detection and mitigation framework for Software-Defined Networking (SDN) based Vehicular Ad-hoc Networks (VANETs) to ensure secure, reliable, and low-latency vehicle-to-infrastructure (V2I) communication.
The system leverages SDN’s centralized control to dynamically monitor network traffic and mitigate DDoS attacks in real time, ensuring uninterrupted safety-critical vehicular services.
Key Innovations:
SDN-Based Centralized Security Control
OpenFlow-enabled SDN controller
Global view of VANET traffic behavior Intelligent DDoS Detection
Flow-level traffic analysis
Anomaly detection using ML / Deep Learning (LSTM Autoencoder / Hybrid model)
Real-Time Mitigation Strategy
Malicious vehicle flow isolation
Dynamic rule installation at RSUs & switches
Rate limiting and blacklisting of attack sources
VANET-Specific Security Awareness
Handles high mobility and dynamic topology
Maintains low latency for safety messages
Technologies Used
SDN Controller: Ryu / ONOS
VANET Simulator: SUMO + Mininet-WiFi
ML/DL Model: LSTM Autoencoder / SVM / Random Forest/ use other technique than LSTM can use multimodel for transfer learning
Dataset: SDN Specifc dataset
Protocols: OpenFlow, TCP/UDP
Programming: Python
Performance Metrics
Detection Accuracy: High (>95%)
False Positive Rate: Low
Mitigation Delay: Minimal
Network Throughput & PDR: Improved post-mitigation
Impact & Use Cases
✔ Secure smart transportation systems
✔ Prevention of service disruption in V2X communication
✔ Applicable to Smart Cities, ITS, Autonomous Vehicles
Designed and implemented an intelligent DDoS detection and mitigation framework for Software-Defined Networking (SDN) based Vehicular Ad-hoc Networks (VANETs) to ensure secure, reliable, and low-latency vehicle-to-infrastructure (V2I) communication.
The system leverages SDN’s centralized control to dynamically monitor network traffic and mitigate DDoS attacks in real time, ensuring uninterrupted safety-critical vehicular services.
Key Innovations:
SDN-Based Centralized Security Control
OpenFlow-enabled SDN controller
Global view of VANET traffic behavior Intelligent DDoS Detection
Flow-level traffic analysis
Anomaly detection using ML / Deep Learning (LSTM Autoencoder / Hybrid model)
Real-Time Mitigation Strategy
Malicious vehicle flow isolation
Dynamic rule installation at RSUs & switches
Rate limiting and blacklisting of attack sources
VANET-Specific Security Awareness
Handles high mobility and dynamic topology
Maintains low latency for safety messages
Technologies Used
SDN Controller: Ryu / ONOS
VANET Simulator: SUMO + Mininet-WiFi
ML/DL Model: LSTM Autoencoder / SVM / Random Forest/ use other technique than LSTM can use multimodel for transfer learning
Dataset: SDN Specifc dataset
Protocols: OpenFlow, TCP/UDP
Programming: Python
Performance Metrics
Detection Accuracy: High (>95%)
False Positive Rate: Low
Mitigation Delay: Minimal
Network Throughput & PDR: Improved post-mitigation
Impact & Use Cases
✔ Secure smart transportation systems
✔ Prevention of service disruption in V2X communication
✔ Applicable to Smart Cities, ITS, Autonomous Vehicles