MSc Thesis Proposal by: Avinash Karhana

The expansion of intelligent transportation systems and their integration into VANETS brings a number of critical safety and security concerns. Among many is the false reporting attack, in which a malicious actor sends adversarial messages to VANET to fabricate artificial traffic incidents. To ensure the safety and reliability of VANET, addressing False Alert Attacks is particularly crucial due to the potential danger that this type of attack poses. False alerts may cause vehicles to take unnecessary evasive actions or divert to avoid non-existent hazards, which might lead to accidents and endanger the safety of drivers, passengers, and other road users. In this research, we aim to address this threat of false alert attacks in VANETs by using the VeReMiAP Dataset (a VeReMi-based dataset) as a benchmark and develop machine learning models and approaches to detect and mitigate false alert attacks in VANETs. The methodology includes a detailed analysis of the dataset, feature engineering in conjunction with plausibility, and the use of state-of-the-art machine learning models for detection. The preliminary results after the detailed analysis of the dataset and feature engineering show significant and performance improvements in detecting false alert attacks using classical ML models. These findings strengthen the idea that machine learning models can be used to detect this attack effectively. This thesis focuses on the importance and urgency of addressing false alert attacks in VANETs and the potential of machine learning models to detect and mitigate strategies to prevent such attacks using the VeReMiAP dataset. This research would be one of the initial attempts to address this type of attack using ML techniques, given that this is a relatively new dataset which introduced this type of attack. The contribution of this research will be to provide a baseline for future research in False Alert attack detection using ML while providing insight into this new attack type and the VeReMiAP dataset itself. The findings of this research are expected to aid in developing more robust and secure vehicle communication networks.

 

Keywords: VANETs, Machine Learning, VeReMiAP Dataset, False Alert Attack, ITS

 

Internal Reader: Dr. Saeed Samet             

External Reader: Dr. Bala Balasingam

Co-Supervisor: Dr. Arunita Jaekel

Co-Supervisor: Dr. Ikjot Saini