An Authentication and Secure Communication Scheme for In-Vehicle Networks Based on SOME/IP

The rapid development of intelligent networked vehicles (ICVs) has brought many positive effects. Unfortunately, connecting to the outside exposes ICVs to security threats. Using secure protocols is an important approach to protect ICVs from hacker attacks and has become a hot research area for vehicle security. However, most of the previous studies were carried out on V2X networks, while those on in-vehicle networks (IVNs) did not involve Ethernet. To this end, oriented to the new IVNs based on Ethernet, we designed an efficient secure scheme, including an authentication scheme using the Scalable Service-Oriented Middleware over IP (SOME/IP) protocol and a secure communication scheme modifying the payload field of the original SOME/IP data frame. The security analysis shows that the designed authentication scheme can provide mutual identity authentication for communicating parties and ensure the confidentiality of the issued temporary session key; the designed authentication and secure communication scheme can resist the common malicious attacks conjointly. The performance experiments based on embedded devices show that the additional overhead introduced by the secure scheme is very limited. The secure scheme proposed in this article can promote the popularization of the SOME/IP protocol in IVNs and contribute to the secure communication of IVNs.

Hierarchical Federated Learning for Edge-Aided Unmanned Aerial Vehicle Networks

Federated learning (FL) allows UAVs to collaboratively train a globally shared machine learning model while locally preserving their private data. Recently, the FL in edge-aided unmanned aerial vehicle (UAV) networks has drawn an upsurge of research interest due to a bursting increase in heterogeneous data acquired by UAVs and the need to build the global model with privacy; however, a critical issue is how to deal with the non-independent and identically distributed (non-i.i.d.) nature of heterogeneous data while ensuring the convergence of learning. To effectively address this challenging issue, this paper proposes a novel and high-performing FL scheme, namely, the hierarchical FL algorithm, for the edge-aided UAV network, which exploits the edge servers located in base stations as intermediate aggregators with employing commonly shared data. Experiment results demonstrate that the proposed hierarchical FL algorithm outperforms several baseline FL algorithms and exhibits better convergence behavior.

Time-Varying Formation Control for Heterogeneous Planar Underactuated Multi-Vehicle Systems

This paper presents a distributed control approach for time-varying formation of heterogeneous planar underactuated vehicle networks without global position measurements. All vehicles in the network are modeled as generic three degree of freedom planar rigid bodies with two control inputs, and are allowed to have non-identical dynamics. Feasible trajectories are generated for each vehicle using the nonholonomic constraints of the vehicle dynamics. By exploiting the cascaded structure of the planar vehicle model, a transformation is introduced to define the reduced order error dynamics, and then, a sliding-mode control law is proposed. Low level controller for each vehicle is derived such that it only requires relative position and local motion information of its neighbors in a given directed communication network. The proposed formation control law guarantees the uniform global asymptotic stability (UGAS) of the closed-loop system subject to bounded uncertainties and disturbances. The proposed approach can be applied to underactuated vehicle networks consisting of mobile robots, surface vessels and planar aircraft. Simulations are presented to demonstrate the effectiveness of the proposed control scheme.

LATTE: L STM Self- Att ention based Anomaly Detection in E mbedded Automotive Platforms

Modern vehicles can be thought of as complex distributed embedded systems that run a variety of automotive applications with real-time constraints. Recent advances in the automotive industry towards greater autonomy are driving vehicles to be increasingly connected with various external systems (e.g., roadside beacons, other vehicles), which makes emerging vehicles highly vulnerable to cyber-attacks. Additionally, the increased complexity of automotive applications and the in-vehicle networks results in poor attack visibility, which makes detecting such attacks particularly challenging in automotive systems. In this work, we present a novel anomaly detection framework called LATTE to detect cyber-attacks in Controller Area Network (CAN) based networks within automotive platforms. Our proposed LATTE framework uses a stacked Long Short Term Memory (LSTM) predictor network with novel attention mechanisms to learn the normal operating behavior at design time. Subsequently, a novel detection scheme (also trained at design time) is used to detect various cyber-attacks (as anomalies) at runtime. We evaluate our proposed LATTE framework under different automotive attack scenarios and present a detailed comparison with the best-known prior works in this area, to demonstrate the potential of our approach.