부산대학교 도서관

The use of vehicles on the road plays a significant role in our daily lives. However, the growing number of vehicles is also contributing to increased occurrences of collisions, traffic jams, air pollution, and other related problems. Recently, the use of Vehicular Adhoc Network (VANET) has been proposed for implementing an intelligent transportation system (ITS), with the aim of alleviating these issues. VANET communication is vulnerable to various types of attacks, and appropriate security mechanisms must be in place to ensure that exchanged messages are not altered or false messages created by malicious attackers. In this paper, we propose a new hybrid approach consisting of a combination of Machine Learning and Plausibility Checks to detect position forgery attacks in basic safety messages (BSMs). Our results indicate that the proposed approach outperforms the existing work available in the literature in terms of different well-accepted performance metrics such as accuracy, precision, recall, and F1-score.