A Transfer Double Deep Q Network Based DDoS Detection Method for Internet of Vehicles
Zhong Li, Yubo Kong, Changjun Jiang
Abstract
Distributed denial of service (DDoS) attacks have become one of the main factors restricting the development of internet of vehicles (IoV). Although some intelligent reinforcement learning based methods have been introduced to mitigate DDoS attacks, there are still many constraints in the training process, such as the long training time and dependence on large labeled data. In this paper, we propose a transfer double deep Q-network (DDQN) based DDoS detection method for IoV. By constructing a Kalman filter based reinforcement learning model, we can constantly improve the performance of DDoS detection in DDQN without depending on large labeled data. Furthermore, by utilizing the knowledge obtained by adjacent similar base stations, we design a transfer DDQN method based on traffic flow similarity to speed up the training of DDQN for a newly added base station. This enables the new base station to obtain DDoS detection policies quickly. We compare our proposed method with other popular machine learning based DDoS detection methods. The experimental results show that the transfer DDQN based DDoS detection method improves F1-measure and detection accuracy by 79.4% and 17.5% on average. Meanwhile, by means of traffic flow similarity based transfer learning, the time consumption and convergence time can be reduced by 41.3% and 31.1%, which makes our method adapt to the dynamic network.