Recently, a number of technologies have been developed to promote vehicular networks. When vehicles are associated with the heterogeneous base stations (e.g., macrocells, picocells, and femtocells), one of the most important problems is to make load balancing among these base stations. Different from common mobile networks, data traffic in vehicular networks can be observed having regularities in the spatial-temporal dimension due to the periodicity of urban traffic flow. By taking advantage of this feature, we propose an online reinforcement learning approach, called ORLA. It is a distributed user association algorithm for network load balancing in vehicular networks. Based on the historical association experiences, ORLA can obtain a good association solution through learning from the dynamic vehicular environment continually. In the long run, the real-time feedback and the regular traffic association patterns both help ORLA cope with the dynamics of network well. In experiments, we use QiangSheng taxi movement to evaluate the performance of ORLA. Our experiments verify that ORLA has higher quality load balancing compared with other popular association methods.

The Internet of Vehicles (IoV) is a subapplication of the Internet of Things in the automotive field. Large amounts of sensor data require to be transferred in real-time. Most of the routing protocols are specifically targeted to specific situations in IoV. But communication environment of IoV usually changes in the space-time dimension. Unfortunately, the traditional vehicular networks cannot select the optimal routing policy when facing the dynamic environment, due to the lack of abilities of sensing the environment and learning the best strategy. Sensing and learning constitute two key steps of the cognition procedure. Thus, in this paper, we present a software defined cognitive network for IoV (SDCIV), in which reinforcement learning and software defined network technology are considered for IoV to achieve cognitive capability. To the best of our knowledge, this paper is the first one that can give the optimal routing policy adaptively through sensing and learning from the environment of IoV. We perform experiments on a real vehicular dataset to validate the effectiveness and feasibility of the proposed algorithm. Results show that our algorithm achieves better performance than several typical protocols in IoV. We also show the feasibility and effectiveness of our proposed SDCIV.

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.

With the development of 5G technology, mobile edge computing (MEC) is introduced into the construction of internet of vehicles (IoV). However, the distributed denial of services (DDoS) attacks become a serious problem in IoV under MEC. Although numbers of studies have been done on DDoS detection in common wired or wireless networks, they cannot satisfy the high dynamic requirement and cannot cope with the complex and diverse DDoS attacks in IoV. Fortunately, the data traffic flows in IoV exist potential and predictable space-time regularities. By employing reinforcement learning, we propose a feature adaption reinforcement learning approach based on the space-time flow regularities in IoV for DDoS mitigation, named FAST. In FAST, we elaborately design a combinational action space, and a reward function based on Kalman filter method and historical data traffic flows, which can make FAST to recognize DDoS attacks more quickly and accurately. Then through combining Q-learning and DDQN, FAST can select features and disconnect DDoS attacks adaptively according to the changes of the environment. In experiments, we evaluate the performance of FAST based on Shenzhen taxicab dataset. We simulate and inject DDoS attacks into Shenzhen taxicabs through two DDoS simulation tools named ‘ddosflowgen’ and ‘hping3’. The experimental results show that FAST has a high quality in detecting multiple types of DDoS attacks compared with other detection methods.

Federated learning is usually utilized as a fraud detection framework in the domain of financial risk management, which promotes the model accuracy without training data exchange. One of the challenges in federated learning is the GAN-based poisoning attack. The GAN-based poisoning attack is a type of intractable poisoning attack that causes global model accuracy degradation and privacy leak. Most of the existing defenses for GAN-based poisoning attack have the three problems: 1) dependence on validation datasets; 2) incompetence of dealing with incremental poisoning attack; and 3) privacy leak. To address the above problems, we present a privacy-aware and incremental defense (PID) method to detect malicious participants and protect privacy. In PID, we design a method to accumulate the offset of model parameters from participants in all current epochs to represent the moving tendency for model parameters. Thus, we can distinguish the adversaries from normal participants based on the accumulations in this incremental poisoning attack. We also use multiple trust domains to reduce the rate of misjudging benign participants as adversaries. Moreover, a differentiated differential privacy is utilized before the global model sending to protect the privacy of participants’ training datasets in PID. The experiments conducted on two real-world datasets under financial fraud detection scenario demonstrate that the PID reduces the fallout of adversaries detection (the rate of misjudging benign participants as adversaries) by at least 51.1% and improve the speed of detecting all malicious participants by at least 33.4% compared with two popular defense methods. Besides, the privacy preserving of PID is also effective.

The issue of transaction security has attracted widespread attention due to the frequent occurrence of financial fraud. Graph neural networks (GNNs) can effectively detect financial fraudulent behavior by capturing transaction relationships. However, many existing methods lack the consideration of modeling user behavior patterns at diverse timescales. Moreover, GNN-based approaches usually fail to adaptively perceive neighborhood information from global and local perspectives, resulting in some transaction node embeddings merging the information from partially irrelevant neighboring transaction nodes and leading to suboptimal performance. Therefore, this work proposes a Multi-Temporal Partitioned graph attention Network (MTPNet) for financial fraud detection. In particular, we design a multi-temporal partitioned graph construction algorithm that generates multi-temporal series graphs at various timescales. These graphs effectively express the periodic variations in users’ transaction behavior pattern, allowing GNNs to learn knowledge from these graphs and extract richer semantic information. Then, we propose a global-local neighborhood-aware encoder to enable transaction node embeddings to adaptively aggregate their most relevant neighborhood information based on the attention mechanism. We perform extensive experiments to evaluate the performance of MTPNet on large-scale financial fraud datasets and demonstrate its effectiveness.