Vision Transformer (ViT) achieves competitive results in person ReID, not only due to the powerful ability on feature representation, but also its resistance to attacks. However, they are vulnerable to specially designed attacks. To enhance their robustness, this paper proposes RobusTReID to defend the ViT-based model against perturbed images without obvious performance drop on clean data. The basic idea is to incorporate the adversarial co-training into ReID, which first disturbs pixels by minimizing adversarial loss in primary feature branch, then optimizes model by ReID task loss computed in all branches on clean and perturbed data. We separate the representation paths for clean and perturbed images. Particularly, a learnable [ADV] token and low-rank positional embeddings (PE) are incorporated to build the feature for perturbed image. Extensive experiments on several ReID datasets show that our method effectively increases the robustness of ReID model under different types of attacks.

Autonomous vehicle platooning has tremendous potential to relieve the burden of Vehicular Edge Computing (VEC) by sharing resources with nearby vehicles. Therefore, fleet formation and resource orchestration within vehicle platoons have recently ignited significant research interest. However, most fleet formation works focus on the intra-platoon configuration and information exchange, but few consider trajectory matching and joining willingness. Likewise, in multi-platoon scenarios, static resource orchestration for a single platoon no longer meets the demand from dynamic resource scheduling. To tackle these problems, we proposed the SFO scheme, an adaptive taskScheduling based on incentive fleetFormation and metrizable resourceOrchestration. First, we design a fleetFormation algorithm based onTrajectory matching andJoining willingness (FTJ) to ensure the stable underlying architecture. Second, we use theWeightedSum ofEnergyConsumption (WSEC) as the performance metric for resource orchestration and formulate the time-average WSEC minimization problem. Third, anAdaptive taskScheduling underPartitionableApplications and variableResources (ASPAR) is proposed for an asymptotic optimal solution in reaction to the changeable backlog of the timeout queue. Finally, our numerical results demonstrate that our approach is superior to other latest and classic works in energy consumption and execution latency.

Utilizing the stable underlying and cloud-native functions of vehicle platoons allows for flexible resource provisioning in environments with limited infrastructure, particularly for dynamic and compute-intensive applications. To maximize this potential, we propose the creation of a trading market to encourage interactions between service supporters (vehicle platoons) and requesters (task vehicles). Current trading decisions based on game and negotiations can lead to unpredicted handover costs and increased communication overhead in dynamic environments. Moreover, existing research tends to overlook a mutually beneficial trading philosophy by focusing on either the service supporters’ profitability or the user experience of resource-restrained requesters. Addressing these issues, we introduce a multi-objective optimization problem to model environmental dynamics and uncertainty, aiming to maximize both platoons’ and task vehicles’ long-term utilities while maintaining a satisfactory service access ratio. To tackle the problem within acceptable time frames, we develop a global-local training architecture, incorporating a hybrid action space and prioritized sampling into a multi-agent reinforcement learning algorithm that utilizes a twin delayed deep deterministic gradient (GL-HPMATD3). This approach facilitates consensus in the trading market on key issues, including service request selection, resource allocation, and trading pricing. Through extensive experimentation and comparison, we demonstrate our mechanism’s superior performance in convergence, service access ratio, player utility, execution latency, and trading pricing relative to several state-of-the-art and baseline methods.

The autonomous vehicle platoon has the potential to cope with the stress caused by the resource-constrained vehicles‘ demand for processing power and the spread-out deployment of MEC-BS. In this poster, we focus on a multi-platoons scenario for task scheduling. Our objective is to minimize the overall energy consumption subject to the long-term latency constraint. To characterize stochastic properties and deal with coupling between variables, we propose a dynamic task scheduling algorithm based on Lyapunov optimization (LDTS). We theoretically and empirically evaluate the performance of the proposed algorithm, which is illustrated to be significantly better than state-of-the-art and other benchmark approaches in terms of execution latency and energy consumption.

The rapid advancement of intelligent vehicles is deemed crucial to the emergence of diverse compute-intensive applications of assisted driving, which consist of automatic driving, speed recognition, hybrid sensing data fusion, etc. Nevertheless, resources-constraint vehicles with high mobility cannot always meet the computing and communication demands when the above applications occur. Additionally, considering the expensive and inflexible deployment of edge servers, offloading application tasks to “Edge” in the vehicular networks is not always working well. To effectively mitigate the above issues, the complicated application tasks are motivated to offload to the vehicle platoon, where the vehicles travel synchronously in a string with small headway. Benefiting from the stable connectivity, adjustable mobility, and reasonable charge, the task vehicle would like to process the task by leveraging the idle resources of each platoon member (PM). To make more effective use of the resources on the mobile edge platoon cloud (MEPC), we investigate the resource allocation strategy based on the task vehicle’s service pricing strategy in this work. We first formulate the interactions between MEPC and task vehicle as a Stackelberg game to study the joint utility maximization of the MEPC and task vehicle. Then the Stackelberg Equilibrium (SE) for the proposed game is characterized and proved. The proposed algorithm Hook-Jeeves-based Stackelberg game (HJSG) can reach the SE. Finally, we introduce the consortium blockchain to ensure the security and privacy of service transactions. The entire system helps enhance task processing efficiency, protect transaction data, and improve service experience. Experimental results over numerical simulation based on practical scenarios demonstrate that compared with Multi-round Stackelberg Game (MRSG), uniform pricing, and the local computation strategy, the proposed HJSG algorithm can attain less execution time and faster convergence performance.

With the rapid development of intelligent transportation, various computation-intensive applications have e-merged to improve the safety, efficiency, and comfort on the road. However, due to the mobility and resource dynamics, it is still a challenge for the resource-constrained vehicles to timely process computation-intensive tasks. Fortunately, the computation offloading in the Internet of Vehicles (IoV) greatly eases the contradiction between resource constraints and computing requirements. In this paper, we first present a collaborative computing architecture based on Edge-Cloud (EC) and Mobile-Edge-Platooning-Cloud (MEPC). Then, considering the priority of the Delay-Sensitive Tasks (DSTs), preemptive scheduling is introduced to deal with the hybrid tasks, comprised of DSTs and Delay-Tolerant Tasks (DTTs). Finally, a computation offloading problem based on the collaborative EC-MEPC architecture is established by jointly optimizing the decision-making and resource allocation issue. To solve the above problem, a distributed computation offloading and resource allocation algorithm is designed to achieve the optimal solution. Simulation results show that the proposed collaborative computing architecture and the distributed algorithm can effectively improve the delay and energy consumption performance of this system.

Most of the existing outsourced encrypted data schemes are retrieved based on the query keyword entered by authorised users.However, with the increase of the data scale in the cloud storage system, the retrieval efficiency of existing solutions has not been significantly improved.In this paper, a multi-keyword ranked search scheme for ciphertext based on mapping set matching (MSMR) is proposed, where (1) The private cloud server matches the keyword numbering set corresponding to the document index vector and the keyword numbering set corresponding to the query vector and sends the document identifier of the matching keyword numbering to the public cloud server.The public cloud server filters the documents irrelevant to the query request according to the document identifier corresponding to the matching keyword numbering, which effectively reduces the time spent in calculating the correlation score, and (2) the document index vector and query vector are segmented before encrypting them out, reducing the time to construct such vectors.Theoretical analysis shows that the proposed scheme is secure in the known ciphertext model.Experimental results confirm that whenever the data scale grows, the improvement of MSMR retrieval efficiency is more significant.

To improve the urban traffic condition and reduce accidents, we propose a platoon-driving model for autonomous vehicles in a free-flow traffic state in this article. This model allows vehicles with successful path matching to be grouped in a platoon and led by the platoon head (PH). In addition, a PH selection scheme is introduced to provide an incentive for vehicles to be PHs and maintain the dynamic update of platoons. Next, a smart contract is employed to enable the payment based on a blockchain between the PH and platoon members (PMs), avoiding the malicious and false payments. The numerical results show that the platoon model is superior to the individual driving model in terms of fuel consumption. The comparison between carpooling and noncarpooling modes within the platoon shows that our model has a better performance in terms of PH revenue and PM's service charge.