| dc.contributor | 資訊系 | |
| dc.creator (作者) | 孫士勝 | |
| dc.creator (作者) | Kuo, Nai-An;Fan, Chia-Hao;Liu, Ping-Chih;Sun, Shi-Sheng | |
| dc.date (日期) | 2025-12 | |
| dc.date.accessioned | 4-May-2026 13:29:33 (UTC+8) | - |
| dc.date.available | 4-May-2026 13:29:33 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-May-2026 13:29:33 (UTC+8) | - |
| dc.identifier.uri (URI) | https://ah.lib.nccu.edu.tw/item?item_id=182282 | - |
| dc.description.abstract (摘要) | The Internet of Vehicles (IoV) connects vehicles, infrastructure, and pedestrians to enable efficient traffic management, autonomous driving, and real-time interactions. However, security concerns have emerged with Sybil attacks, where attackers forge multiple identities posing a serious threat. While many machine learning approaches have been used to detect Sybil nodes, they often result in high computational and communication costs. To address this, we proposed an efficient two-stage Sybil detection method that integrates rule-based techniques with deep learning. In the first stage, vehicles implement individual detection, and Roadside Units (RSUs) collect vehicle broadcast data to detect anomalies. Upon detection, data is sent to a central IoV server, where a deep learning model analyzes time-series data to accurately identify Sybil nodes, thus enhancing detection accuracy while reducing system overhead. | |
| dc.format.extent | 108 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | IEEE AIoT 2025 Conference Proceedings, IEEE Internet of Things Community, pp.262-270 | |
| dc.subject (關鍵詞) | Internet of Vehicles (IoV); Sybil attack; Deep learning; Rule-based; Attack detection | |
| dc.title (題名) | Hybrid Sybil Attack Detection in IoV Networks Using Rule-Based and Deep Learning Methods | |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1109/AIoT66900.2025.00047 | |
| dc.doi.uri (DOI) | https://doi.org/10.1109/AIoT66900.2025.00047 | |
