Keep Your Data Locally: Federated-Learning-Based Data Privacy Preservation in Edge Computing

Edge computing is an emerging novel computation paradigm, which plays a vital role in the 5G era. A basic application scenario in edge computing is that end users have the ability to choose edge server nodes, which are expected to participate in working on the tasks allocated by end users. At the same time, edge server nodes can freely make their own decisions on serving, which end user's task. End users have to compete with each other for edge server nodes’ service, through the payment they can offer to edge nodes for service. In this paper, we apply game theory to model the interaction between end users and edge server nodes as a noncooperative game. The end users are the players who compete for service, and the edge server nodes are the ones who provide service. We have proved the existence of Nash Equilibrium in the game, which suggests that there exists a stable system state in the edge computing environment. We have also shown the stability of the Nash Equilibrium in a best response dynamic game playing process, which further indicates that the stable system state can be reached in practice where end users dynamically adjusting their strategies in the process of competing for edge computing resources provided by server nodes.

Edge computing or edge networking is an architecture that uses one or more collaborative multitude of end-user clients or near-user edge devices to carry out a substantial amount of communication, control, management or other operations. Edge Computing for mobile networks is a new technology which is currently under standardization providing an IT service environment and cloud-computing capabilities at the edge of the mobile network in close proximity to the mobile end users. The aim of this technology is to reduce latency, ensure highly efficient network operation and service delivery, providing improved user experience. All of these can be translated into value and can create opportunities for operators, application and content providers enabling them to better utilize the mobile broadband capabilities. Furthermore, edge computing enables a new value chain for end users but also for industries allowing to efficient deliver their applications over the mobile network providing fresh business opportunities and new use cases. FEC is a feedback free error recovery method where the sender introduces redundant data in advance with the source data enabling the recipient to recover from different arbitrary packet losses. Recently, the adoption of FEC error control method has been boosted by the introduction of the powerful RaptorQ Application Layer FEC (AL-FEC) codes. In this work we propose the integration of AL-FEC error protection application at the edge layer. We propose a novel AL-FEC application architecture scheme based on RaptorQ codes and we analyze the performance enhancements such an error control architecture can introduce on Next Generation Mobile Networks (NGMN)-edge computing integrated systems.

The main intention of edge computing is to improve network performance by storing and computing data at the edge of the network near the end user. However, its rapid development largely ignores security threats in large-scale computing platforms and their capable applications. Therefore, Security and privacy are crucial need for edge computing and edge computing based environment. Security vulnerabilities in edge computing systems lead to security threats affecting edge computing networks. Therefore, there is a basic need for an intrusion detection system (IDS) designed for edge computing to mitigate security attacks. Due to recent attacks, traditional algorithms may not be possibility for edge computing. This article outlines the latest IDS designed for edge computing and focuses on the corresponding methods, functions and mechanisms. This review also provides deep understanding of emerging security attacks in edge computing. This article proves that although the design and implementation of edge computing IDS have been studied previously, the development of efficient, reliable and powerful IDS for edge computing systems is still a crucial task. At the end of the review, the IDS developed will be introduced as a future prospect.

A Novel Lyapunov based Dynamic Resource Allocation for UAVs-assisted Edge Computing

The use of machine learning models trained on imbalanced datasets with sensitive information has raised privacy concerns. One significant threat is the Membership Inference Attack (MIA), which tries to figure out if a particular data point was included in the training set. This paper investigates whether algorithm-level cost-sensitive learning poses a greater privacy leakage risk than data-level sampling. We conducted experiments using two datasets: the UCI Adult dataset, which focuses on predicting income, and the APS dataset, which focuses on predicting scientific productivity. Our results indicate that models trained with cost-sensitive learning are more vulnerable to MIAs. This supports the hypothesis that correcting for imbalances at the algorithm level can reveal more private information.

Intelligent task prediction and computation offloading based on mobile-edge cloud computing

The growing scale of smart city sensing devices and infrastructure entails a wide variety of available sensing information that can provide valuable insights into user mobility and traffic congestion. This information can be used to optimize service delivery through the development of mobility-aware services. 5G systems and their associated technologies provide an ideal environment with capabilities to efficiently support edge computing and bring the processing and storage resources closer to the end users, which results in a latency and backhaul usage reduction. This article proposes the integration of edge computing in 5G operator network and a mobility/road-side infrastructure with edge orchestration to provide mobility-aware services to the end-users on demand. With this approach, a service instantiation can be translated into resource allocation both on the 5G platform through multi-slicing and the edge infrastructure. Resource management is then optimized for the users on the move by continuously allocating the necessary virtual network slices, processing, and storage resources in the appropriate locations for the user to consume its services while maintaining the appropriate QoS levels and optimized resource distribution in the edge platform. This approach is evaluated in a real mobile 5G network with emulated Radio Access Network (RAN) resources through two use cases based on infotainment and emergency services. The results show that the approach is efficient in using mobility, service requirements, and platform’s resources information to enable a proactive resource reservation both in the 5G base stations and edge computing nodes throughout the path traversed by the users. • Smart City sensing and mobility information can be used to optimize service delivery. • The integration of mobility, MEC and 5G enable the instantiation of emergency services. • Allocation of the network and computing resources, maintaining the required QoS levels. • Results successfully demonstrate proactive resource reservation in both 5G and MEC.

Edge computing has been widely used in recent years for bringing services closer to end users, resulting in faster response for applications. However, the sensitive information that leaves the data owner is at risk of being disclosed because the service provider is generally honest-but-curious. Federated learning (FL) is a popular method for preserving privacy by transferring the model from the edge node to local devices and training on the local data set. Nonetheless, the training parameter that communicates between local mobile devices and the edge node may contain the original data and be guessed by adversaries. In order to address the privacy threats, we propose the PL-FedIPEC scheme in this article, which is a privacy-preserving and low-latency FL method that transmits parameters encrypted with the improved Paillier, a homomorphic encryption algorithm, to protect the privacy of end devices without transmitting data to the edge node. Our method introduces the improved Paillier encryption, which brings a new hyperparameter and previously computes multiple random intermediate values in the key generation phase so that the time for the encryption phase has a significant reduction. With this new algorithm, the time for model training is decreased, and the sensitive information is in ciphertext format and cannot be analyzed. To evaluate the efficiency of our proposed scheme, we conduct extensive experiments and the results validate and demonstrate that our scheme with the improved Paillier algorithm can achieve the same accuracy as the original Paillier algorithm and the baseline FedAVG algorithm. At the same time, our method can save a massive amount of time when training the learning model with various settings.

Edge computing has been regarded as an enabling technology for supporting future smart applications, such as industrial Internet of Things. In this paper, a novel computation offloading framework for edge computing is proposed. Unlike existing studies, this work considers that end users can intentionally reserve some time for local pre-processing before requesting the computation offloading service (instead of always declaring their offloading requests immediately when heavy-duty tasks are generated). By doing so, each task’s offloading cost may decrease because of less edge resource demand, while the delay cost may increase due to the later report of its offloading request. Furthermore, end users can select their preferred priority levels in the offloading scheduling by paying premium service charges. To maximize the individual utility, each end user may strategically and jointly determine its local pre-processing time-length and priority selection in computation offloading. For characterizing strategic interactions among end users and the quality-of-service (QoS) of the scheduling system with congested nature, a computation offloading game built upon a queueing model is formulated. On top of this, a revenue maximization problem for the interest of edge operator is also investigated. Simulations evaluate the performance of the proposed solution, and shows its superiority over counterparts.

Edge computing is an emerging computing paradigm, which extends the functions of cloud center to the edge of the networks, and brings great convenience to solving problems of delay and bandwidth in the traditional cloud computing paradigm. In edge computing architecture, one-to-many communication is a important communication mode that supports the edge nodes to send one message to multiple terminal devices in one broadcast report. To build a secure one-to-many communication, several multi-receiver signcryption (MRSC) schemes have been brought forward to ensure the security of broadcast messages. However, the existing MRSC schemes need the heavy computation and communication cost, and is not suitable for IoT terminal devices with limited resources. Besides, most of the existing MRSC schemes are vulnerable to the security and privacy leakage, and fail in achieving the decryption fairness. To solve these problems, based on the implicit certificate (IC) cryptosystem and polynomial interpolation evaluation, this paper proposes an provably secure multi-receiver IC-based signcryption (MRICSC) scheme for one-to-many communication in edge computing. The security analysis evidences the proposed MRICSC scheme can ensure the security. With the experimental results indicating that the proposed MRICSC scheme achieves the better performance than existing schemes.

Joint edge caching and dynamic service migration in SDN based mobile edge computing

Edge computing emerged as a promising paradigm that provides cloud-like services in the vicinity of mobile users. Benefitting from the geographical and social similarities among users, edge computing can intelligently provide on-demand services with low latency. However, the unprecedented amount of tasks along with the heterogeneous nature of applications in future smart cities such as healthcare, energy management, transportation, cybersecurity, and so on, have created a bottleneck on the performance of edge computing. Therefore, edge devices need to be equipped with adaptive machine learning techniques to cope with the continuously changing computing environment and to provide mobile users with reliable smart services. Furthermore, establishing a cloud-to-edge and edge-to-edge cooperative learning can help not only to relieve the burdens on edge servers but also to facilitate the learning process in which the knowledge earned by one computing node can be shared by other nodes in the network. In this paper, edge computing services are presented in light of state-of-the-art machine learning and computing technologies. In addition, a case study on edge-assisted multi-hop D2D communications for IoT devices is proposed aiming to provide seamless connectivity and reduce delay in dense IoT environments.

To better support emerging interactive mobile applications such as those VR-/AR-based, cloud computing is quickly evolving into a new computing paradigm called edge computing. Edge computing has the promise of bringing cloud resources to the network edge to augment the capability of mobile devices in close proximity to the user. One big challenge in edge computing is the efficient allocation and adaptation of edge resources in the presence of high dynamics imposed by user mobility. This paper provides a formal study of this problem. By characterizing a variety of static and dynamic performance measures with a comprehensive cost model, we formulate the online edge resource allocation problem with a mixed nonlinear optimization problem. We propose MOERA, a mobility-agnostic online algorithm based on the “regularization” technique, which can be used to decompose the problem into separate subproblems with regularized objective functions and solve them using convex programming. Through rigorous analysis we are able to prove that MOERA can guarantee a parameterized competitive ratio, without requiring any a priori knowledge on input. We carry out extensive experiments with various real-world data and show that MOERA can achieve an empirical competitive ratio of less than 1.2, reduces the total cost by $4 \times$4× compared to static approaches, and outperforms the online greedy one-shot solution by 70 percent. Moreover, we verify that even being future-agnostic, MOERA can achieve comparable performance to approaches with perfect partial future knowledge. We also discuss practical issues with respect to the implementation of our algorithm in real edge computing systems.

Emerging Internet of Things (IoT) applications share the same characteristics of involving multiple processing components ( i.e. , function modules) and requiring a massive amount of data to be processed with low latency. To meet these needs, edge/fog computing has been proposed for next-generation mobile networks to migrate the computing from the cloud to the edge of the network. Thanks to the development of Network Functions Virtualization (NFV), with which edge computing platform can virtualize function modules and deploy them on any edge devices to provide flexible services on the edge networks. However, such platform would need to deal with complicated function module calling relationship ( i.e. , call graph) of applications and user mobility, and both are not thoroughly considered by existing works of NFV and edge computing. In this paper, based on our previous idea of virtual local-hub (VLH), we propose a complete design of edge computing framework, which applies NFV technology on edge computing environment for IoT applications. To handle the complicated call graphs of IoT applications with better resource utilization, the VLH framework adapts the technologies of container-based virtualization and microservice architecture, which enables remote function module sharing on the edge computing environment. The framework includes the heuristic algorithm for function module allocation with the objective of minimizing total bandwidth consumption. We also present a design of protocols for system operations and mobility handling in the framework. Then we implement the framework on commodity hardware as a testbed. Via simulations under a large-scale environment with practical settings and experiments on the testbed under real-world scenarios, we demonstrate and verify the effectiveness and practicability of the proposed VLH framework for IoT application service provision.

Edge computing has been widely adopted in many systems, thanks for its advantages to offer low latency and alleviate heavy request loads from end users. Its integration with indoor positioning is one of promising research topics. Different from a traditional positioning system where a user normally query remotely deployed positioning services provided by a Location Information Service Provider (LIS), LIS will outsource its service to an edge device, and the user can obtain the service by directly accessing the edge device in an edge computing-based system. Though the benefits from edge computing, there is still some open issues for service outsourcing. One of them is how to ensure that the outsourced service is executed honestly by the edge device. However, the current literature has not yet seriously studied this issue with a feasible solution. In this paper, we design a verification scheme to solve this open problem for indoor positioning based on edge computing. By injecting some specially designed dataset into a trained machine learning based positioning model, the functionality of outsourced model on edge devices can be verified through this dataset with regard to its prediction accuracy from outsourced model. The verification is successful only when the prediction accuracy can pass a threshold. In experiments, we provide extensive empirical evidence using state-of-the-art positioning models based on real-world datasets to prove the effectiveness of our proposed scheme and meanwhile investigate the effects caused by different factors.