International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 11 Issue: 8s DOI: https://doi.org/10.17762/ijritcc.v11i8s.7230 Article Received: 30 April 2023 Revised: 18 June 2023 Accepted: 30 June 2023 ___________________________________________________________________________________________________________________ 491 IJRITCC | July 2023, Available @ http://www.ijritcc.org Attack Classification and Detection for Misbehaving Vehicles using ML/DL Saleha Saudagar 1 , Dr. Rekha Ranawat 2 1 Computer Science and Engineering SAGE University, Indore India salehasaudagar@gmail.com 2 Computer Science and Engineering SAGE University, Indore India rekharathod23@gmail.com Abstract— Vehicle ad hoc networks are a crucial component of the next Intelligent Transportation System created to build a reliable and secure connection between various network components to establish a safe and effective transportation network. Because of open nature of VANETs become vulnerable to numerous assaults such forgery, Denial-of-Service (DoS), and false reports, which can ultimately cause traffic jams or accidents The earlier study concentrated on misbehaving vehicles rather than RSUs. Proposed method integrates data from two subsequent BSMs for testing and training by employing machine learning (ML) methods. The framework merges the data from two BSMs in the right manner and utilizes machine learning/Deep learning methodology which identify the running vehicle as a legal or hostile one. Keywords- Vehicular ad hoc network(VANET), Smart transportation System(STS), Bi-GRU,Intrusion detection system(IDS), Misbehaviour Detection System(MVDS),Machine Learning, Deep Learning. I. INTRODUCTION In today’s scenario road accidents are major reason of rising mortality rate for the people of age from 5 to 30 years. As per the survey of World Health Organization's (WHO), the report generated in 2018 Global Status Report on Road Safety [1]. Vehicular communication [2] are a crucial component of the futuristics Smart Transportation System [3] created to build a reliable and secure connection between various network components to establish a safe and effective transportation network. Vehicle to vehicle and vehicle to infrastructure communication are made possible via the Vehicular infrastructure (also known as VANET), a form of Mobile ad hoc network (MANET) [4]. Vehicle communication has become more prevalent thanks to telecommunications advancements such as the use of high-definition mapping, intelligent transportation systems, autonomous driving, and coordinated driving [5]. While doing so, it also draws attention to the key traits of VANETs, such as self-operated, decentralized infrastructure where each vehicle coming and leaving the range are responsible for communication, and one of the most dynamic topologies [6]. When compared to traditional networks, these communication features provide significant problems and distinctions in terms of security and safety requirements [7, 8]. Exchange of messages are mainly navigation messages, and event-oriented communications, are hardly ever encrypted in automotive communication networks [9]. Because of this, the open nature of VANETs makes them vulnerable to numerous assaults such forgery, Denial-of-Service (DoS), and false reports, which can ultimately cause traffic jams or accidents [10-12]. Drivers are really put at risk since malicious groups may also monitor participants' messages and identity. Therefore, malevolent vehicles for VANETs should be tracked down and punished in the case of any misbehavior [13, 14] from the perspective of maintaining security. Traditional prediction- based protocols have been developed for a variety of specialized applications, including routing, traffic control, safety, and others. To improve performance, Machine Learning (ML) technique for further data analytics, has been encouraged. By examining the data flow in the VANET system, various machine learning algorithms reveal these issues. At various VANET components, numerous types of data are produced. Road Side installed Devices, Various Vehicles, and the Central communication authority, all have access to data such as the specifics of nearby vehicles in the range, routing information, congestion-related information, weather-related information, and any information related with communication among vehicular infrastructure. Due to the dynamic nature of VANET, this tremendous volume of data is constantly generated. Various