This is the accepted version of the paper.This version of the publication may differ from the final published version. Abstract-In this work, an Intrusion Detection System (IDS) for vehicular ad hoc networks (VANETs) is proposed and evaluated. The IDS is evaluated by simulation in presence of rogue nodes that can launch different attacks. The proposed IDS is capable of detecting a false information attack using statistical techniques effectively and can also detect other types of attacks. First, the theory and implementation of the VANET model that is used to train the IDS is discussed. Then an extensive simulation and analysis of our model under different traffic conditions is conducted to identify the effects of these parameters in VANETs. In addition, the extensive data gathered in the simulations is presented using graphical and statistical techniques. Moreover, rogue nodes are introduced in the network and an algorithm is presented to detect these rogue nodes. Finally, we evaluate our system and observe that the proposed application layer IDS based on cooperative information exchange mechanism is better for dynamic and fast moving networks such as VANETs as compared to other techniques available.
Permanent repository link