Sybil Attack Prediction on Vehicle Network Using Deep Learning
| Autor: | null Zulfahmi Helmi, null Ramzi Adriman, null Teuku Yuliar Arif, null Hubbul Walidainy, Maya Fitria |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi); Vol 6 No 3 (2022): Juni 2022; 499-504 |
| ISSN: | 2580-0760 |
| Popis: | Vehicular Ad Hoc Network (VANET) or vehicle network is a technology developed for autonomous vehicles in Intelligent Transportation Systems (ITS). The communication system of VANET is using a wireless network that is potentially being attacked. The Sybil attack is one of the attacks that occur by broadcasting spurious information to the nodes in the network and could cause a crippled network. The Sybil strikes the network by camouflaging themselves as a node and providing false information to nearby nodes. This study is conducted to predict the Sybil attack by analyzing the attack pattern using a deep learning algorithm. The variables exerted in this research are time, location, and traffic density. By implementing a deep learning algorithm enacting the Sybil attack pattern and combining several variables, such as time, position, and traffic density, it reaches 94% of detected Sybil attacks. Vehicular Ad Hoc Network (VANET) or vehicle network is a technology developed for autonomous vehicles in Intelligent Transportation Systems (ITS). The communication system of VANET is using a wireless network that is potentially being attacked. The Sybil attack is one of the attacks that occur by broadcasting spurious information to the nodes in the network and could cause a crippled network. The Sybil strikes the network by camouflaging themselves as a node and providing false information to nearby nodes. This study is conducted to predict the Sybil attack by analyzing the attack pattern using a deep learning algorithm. The variables exerted in this research are time, location, and traffic density. By implementing a deep learning algorithm enacting the Sybil attack pattern and combining several variables, such as time, position, and traffic density, it reaches 94% of detected Sybil attacks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|