Design of an intrusion detection system in VANET

• Main Author: Huang, Yunfan
• Other Authors: Li Kwok Hung
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: https://hdl.handle.net/10356/157542
• Institution: Nanyang Technological University

Vehicle Ad Hoc Network (VANET) is one of the most important approaches for intelligent vehicles to communicate under complex road conditions. However, as VANET is working under wireless and complex conditions, it is under the threat of hacker attacks. One efficient solution to counter hacker attacks is the Intrusion Detection System (IDS), which can detect intrusions to VANET based on various statistics-based or denylist/safelist-based. However, besides safelist IDS, most other IDS approaches have a problem that they can only handle the known attacks when the IDS is designed/trained. For unknown attacks, most IDS become inefficient. A blockchain-based Lifetime Learning IDS (LL-IDS) framework is designed to solve this problem. It applies a blockchain to store uncertain data that IDS cannot decide and is highly likely to be the new attack. With the help of traditional security agencies such as universities, these uncertain data can be labeled can use to train the IDS model. Incremental learning models are shown to have great potential in this condition. This paper introduces a novel IDS named ILL-IDS, an incremental IDS based on LL-IDS. Numerical experiments show that the computational time consumption and web payload can be decreased by applying the ILL-IDS to a public VANET dataset with attack data.