Who are We

Vehicular Ad-hoc Networks (VANETs) have emerged as a vital area of research and play a crucial role in the development of Intelligent Transportation Systems (ITS). The exponential growth in the number of vehicles equipped with advanced computing technologies and wireless communication devices has paved the way for innovative application scenarios that were previously unattainable. In this era of modern connectivity, the Internet of Vehicles (IoV) has become an emerging paradigm, extending the capabilities of VANETs by leveraging the core principles of the Internet of Things (IoT). IoV enables vehicles to autonomously communicate with each other and with roadside units (RSUs), often with little or no human intervention. However, this level of autonomy necessitates robust authentication mechanisms to ensure that entities can reliably identify each other and maintain the integrity and confidentiality of exchanged data. Without such mechanisms, the network becomes vulnerable to malicious actors, potentially compromising safety and privacy. Given the highly dynamic and decentralized nature of IoV environments, traditional centralized authentication systems are often insufficient and infeasible. To address these challenges, Artificial Intelligence (AI) and Machine Learning (ML) techniques are increasingly being integrated into IoV architectures. These technologies enable real-time threat detection, anomaly identification, and adaptive security measures. For instance, ML algorithms can learn from historical traffic patterns to detect unusual behaviors that may indicate cyber-attacks, while AI-driven systems can dynamically adjust security protocols based on contextual information. By embedding AI/ML into IoV, it becomes possible to build intelligent, scalable, and resilient cybersecurity frameworks capable of defending against evolving threats in real-time. This convergence of VANETs, IoV, and AI/ML technologies represents a significant leap forward in realizing the vision of safer, smarter, and more secure transportation systems.

  • This laboratory is equipped with licensed EXata Network Emulator Software, Duckiebots Setup, Implementation of Real-Time Vehicular Networks Testbed (using OBU & RSU) and open sources software such as ns2/ns3 and OmNet ++ among many others.
  • The students also get hands-on with experiments using Network Hardware (i.e., IoT devices, Raspberry Pi, Routers, Switches, Firewalls, PCs, Servers, Laptops, Sensors, and Arduino) which help to monitor network usage, bandwidth, throughput, delay and security attacks.
  • Additionally, Artificial Intelligence (AI) and Machine Learning (ML) concepts are applied for tasks such as traffic prediction, anomaly detection, and smart healthcare analytics, with support for server-based model training, dataset handling, and deployment of intelligent models on edge and cloud platforms.