对于边缘计算缓存的安全策略
Security in Mobile Edge Caching with Reinforcement Learning
L. Xiao, X. Wan, C. Dai, X. Du, X. Chen and M. Guizani, “Security in Mobile Edge Caching with Reinforcement Learning,” in IEEE Wireless Communications, vol. 25, no. 3, pp. 116-122, JUNE 2018, doi: 10.1109/MWC.2018.1700291.
DOI: 10.1109/MWC.2018.1700291
Published in: IEEE Wireless Communications ( Volume: 25, Issue: 3, JUNE 2018)
Liang Xiao; Xiaoyue Wan; Canhuang Dai; Xiaojiang Du; Xiang Chen; Mohsen Guizani
移动边缘计算通常使用缓存来支持5G移动互联网中的多媒体内容，以减少计算开销和延迟。 移动边缘缓存（MEC）系统容易受到各种攻击，例如拒绝服务攻击和流氓边缘攻击。
Mobile edge computing usually uses caching to support multimedia contents in 5G mobile Internet to reduce the computing overhead and latency. Mobile edge caching (MEC) systems are vulnerable to various attacks such as denial of service attacks and rogue edge attacks.

这篇论文应用了强化学习（RL）技术的安全解决方案，以向边缘节点提供安全的卸载以防止干扰攻击。 他们还提出了轻量级身份验证和安全的协作缓存方案，以保护数据隐私。
we propose security solutions that apply reinforcement learning (RL) techniques to provide secure offloading to the edge nodes against jamming attacks. We also present lightweight authentication and secure collaborative caching schemes to protect data privacy.
基于物理层面
Enhancing Information Security via Physical Layer Approaches in Heterogeneous IoT With Multiple Access Mobile Edge Computing in Smart City
D. Wang, B. Bai, K. Lei, W. Zhao, Y. Yang and Z. Han, “Enhancing Information Security via Physical Layer Approaches in Heterogeneous IoT With Multiple Access Mobile Edge Computing in Smart City,” in IEEE Access, vol. 7, pp. 54508-54521, 2019, doi: 10.1109/ACCESS.2019.2913438.
DOI: 10.1109/ACCESS.2019.2913438
Published in: IEEE Access ( Volume: 7)
Dong Wang; Bo Bai; Kai Lei; Wenbo Zhao; Yanping Yang; Zhu Han
因此，本文基于MA-MEC的物联网，从物理层的角度研究了解决安全威胁的方法，因为物理层安全技术具有实现完全保密性、低计算复杂度和资源消耗以及对信道变化的良好适应性等优点。具体来说，我们研究了安全窃听编码、资源分配、信号处理、多节点协作以及物理层密钥生成和身份验证，以应对新出现的安全挑战。
However, deploying cloud computing capability within the radio access network may face serious security threats, which stem from not only the existing technologies and networks but also the MA-MEC-based IoT itself. Therefore, in this paper, the solutions to address the security threats are investigated from physical layer perspectives, since physical layer security technologies have the advantages of achieving perfect secrecy, low-computational complexity, and resource consumption, and good adaptation for channel changes. Specifically, we investigate the secure wiretap coding, resource allocation, signal processing, and multi-node cooperation, along with physical layer key generation and authentication, to cope with the emerging security challenges. Finally, the paper is concluded with some possible future research directions.
Joint Optimization of Offloading and Resources Allocation in Secure Mobile Edge Computing Systems
J. -B. Wang, H. Yang, M. Cheng, J. -Y. Wang, M. Lin and J. Wang, “Joint Optimization of Offloading and Resources Allocation in Secure Mobile Edge Computing Systems,” in IEEE Transactions on Vehicular Technology, vol. 69, no. 8, pp. 8843-8854, Aug. 2020, doi: 10.1109/TVT.2020.2996254.
DOI: 10.1109/TVT.2020.2996254
Published in: IEEE Transactions on Vehicular Technology ( Volume: 69, Issue: 8, Aug. 2020)
Jun-Bo Wang; Hui Yang; Ming Cheng; Jin-Yuan Wang; Min Lin; Jiangzhou Wang
物理层安全技术确保卸载数据的安全传输。
physical layer security techniques canensure the secure transmission of the offloading data.
为了避免信息泄漏到窃听者，我们提出了安全的卸载约束条件，即每个MD上的卸载率不能超过其对AP的可实现的保密率。
To avoid offloading information leakage to the eaves-dropper, we propose secure offloading constraints that the offloading rate at each MD cannot exceed its achievablesecrecy rate to the access point (AP).
Secure MISO Cognitive-Based Mobile Edge Computing With Wireless Power Transfer
J. Wang, B. Liu and L. Feng, “Secure MISO Cognitive-Based Mobile Edge Computing With Wireless Power Transfer,” in IEEE Access, vol. 8, pp. 15518-15528, 2020, doi: 10.1109/ACCESS.2020.2967221.
DOI: 10.1109/ACCESS.2020.2967221
Published in: IEEE Access ( Volume: 8)
Jin Wang; Boyang Liu; Ling Feng
提出了一种基于认知的安全MISO WPT-MEC框架。考虑一个由多天线主发射机（PT）、多天线副基站（SBS）、单天线主接收机（PR）和单天线MD组成的CR网络，SBS作为一个安全的协作中继来提高PT的传输速率，并使用WPT对MD进行充电，从而提前完成PT传输并获得频谱接入机会，以便MD执行MEC。
A secure MISO cognitive-based WPT-MEC framework is proposed. Consider a CR network consists of a multi-antenna primary transmitter (PT), a multi-antenna secondary base station (SBS), a single-antenna primary receiver (PR) and a single-antenna MD. The SBS acts as a secure cooperative relay to improve the transmit rate of the PT and charge the MD using WPT, which could lead to earlier completion of the PT’s transmission and obtain spectrum access opportunities for the MD to execute MEC.
Physical-Layer Assisted Secure Offloading in Mobile-Edge Computing
X. He, R. Jin and H. Dai, “Physical-Layer Assisted Secure Offloading in Mobile-Edge Computing,” in IEEE Transactions on Wireless Communications, vol. 19, no. 6, pp. 4054-4066, June 2020, doi: 10.1109/TWC.2020.2979456.
DOI: 10.1109/TWC.2020.2979456
Published in: IEEE Transactions on Wireless Communications ( Volume: 19, Issue: 6, June 2020)
Xiaofan He; Richeng Jin; Huaiyu Dai
本文提出了一种新的物理层辅助安全卸载方案，即边缘服务器主动广播干扰信号以阻止窃听，并利用全双工通信技术有效地抑制自干扰。寻找最佳干扰信号和相应的最优卸载比是一个具有挑战性的双层优化问题。利用安全卸载问题的特殊结构，开发了高效的卸载算法。
With this consideration, a novel physical-layer assisted secure offloading scheme is proposed in this work, in which the edge server proactively broadcasts jamming signals to impede eavesdropping and leverages full-duplex communication technique to effectively suppress the self-interference. Finding the optimal jamming signal and the corresponding optimal offloading ratio turns out to be a challenging bilevel optimization problem. The special structure of the secure offloading problem is exploited to develop efficient offloading algorithms. Numerical results are presented to validate the effectiveness of the proposed scheme.
移动边缘服务器之间交换安全密钥
DisCO: A Distributed and Concurrent Offloading Framework for Mobile Edge Cloud Computing
K. Ko, Y. Son, S. Kim and Y. Lee, “DisCO: A distributed and concurrent offloading framework for mobile edge cloud computing,” 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN), Milan, 2017, pp. 763-766, doi: 10.1109/ICUFN.2017.7993896.
DOI: 10.1109/ICUFN.2017.7993896
Published in: 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN)
Kwangman Ko; Yunsik Son; Soongohn Kim; Yangsun Lee
开发了一种分布式并发卸载框架DisCO。设计了一种安全机制技术来解决安全问题将一部分IoT应用程序卸载到移动设备时可能会发生边缘服务器或交换数据以进行之间的同时处理
移动边缘服务器
Additionally,
we designed a security mechanism technology to solve security issues
that may occur when offloading a part of IoT application to mobile
edge server or exchanging data for simultaneous processing between
mobile edge servers
一个安全管理器，可以解释和验证在移动边缘服务器之间交换的安全密钥和加密数据。
a security manager that can interpret and verify the security key and encrypted data ex-
changed between mobile edge servers.
隐私感知数据卸载方法（PDO）
Privacy-Aware Data Offloading for Mobile Devices in Edge Computing
X. Xu, B. Tang, G. Jiang, X. Liu, Y. Xue and Y. Yuan, “Privacy-Aware Data Offloading for Mobile Devices in Edge Computing,” 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA, 2019, pp. 170-175, doi: 10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00049.
DOI: 10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00049
Published in: 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
Xiaolong Xu; Bowei Tang; Gaoxing Jiang; Xihua Liu; Yuan Xue; Yuan Yuan
为了防止边缘计算卸载不泄露隐私数据本文提出边缘计算中的隐私感知数据卸载方法（PDO）
In repose to this requirement, a privacy-aware data offloading method (PDO) in edge computing is proposed in this paper.
从技术上讲，对边缘计算中数据卸载的隐私性进行了形式化分析方式。
Technically, the privacy of the data offloading in edge computing is analyzed in a formalized
way.
并且改进了强度对等进化算法（SPEA2）用于共同实现减少数据传输时间并增加隐私熵。
An improved of strength pareto evolutionary algorithm(SPEA2) is adopted to realize jointly optimization to reduce the time of data transmission and increase the privacy entropy.
还进行了广泛的实验评估，以证明该方法的安全性。
Extensive experimental evaluations are conducted to prove the security of the method.
网络攻击检测
Deep Learning Enabled Data Offloading With Cyber Attack Detection Model in Mobile Edge Computing Systems
T. Gopalakrishnan et al., “Deep Learning Enabled Data Offloading With Cyber Attack Detection Model in Mobile Edge Computing Systems,” in IEEE Access, vol. 8, pp. 185938-185949, 2020, doi: 10.1109/ACCESS.2020.3030726.
DOI: 10.1109/ACCESS.2020.3030726
Published in: IEEE Access ( Volume: 8)
T. Gopalakrishnan; D. Ruby; Fadi Al-Turjman; Deepak Gupta; Irina V. Pustokhina; Denis A. Pustokhin; K. Shankar
本文提出了一种新的基于DL的流量预测，其数据卸载机制具有网络攻击检测（DLTPDO-CD）技术。
In this view, this paper presents a new DL based traffic prediction with a data offloading mechanism with cyber-attack detection (DLTPDO-CD) technique.
通过藤壶配合优化器（BMO）算法（称为BMO-DBN）优化的深信网络（DBN）被用作MEC中网络攻击的检测工具。
a deep belief network (DBN) optimized by a barnacles mating optimizer (BMO) algorithm called BMO-DBN is applied as a detection tool for cyberattacks in MEC.
在线安全感知边缘计算
Secure Mobile Edge Computing in IoT via Collaborative Online Learning
B. Li, T. Chen and G. B. Giannakis, “Secure Mobile Edge Computing in IoT via Collaborative Online Learning,” in IEEE Transactions on Signal Processing, vol. 67, no. 23, pp. 5922-5935, 1 Dec.1, 2019, doi: 10.1109/TSP.2019.2949504.
研究了在干扰攻击下的在线安全感知边缘计算。
In this context, thepresent paper deals with online security-aware edge computingunder jamming attacks.
利用MAB工具，在对抗性随机干扰的情况下，开发了两种利用边缘计算进行交易的算法
Leveraging MAB tools, we develop two algorithms todeal with edge computing in the presence of adversarialand stochastic jamming attacks.

服务器端风险，提出了一种风险感知计算卸载（RCO）策略
Risk-aware Edge Computation Offloading UsingBayesian Stackelberg Game
Y. Bai, L. Chen, L. Song and J. Xu, “Risk-Aware Edge Computation Offloading Using Bayesian Stackelberg Game,” in IEEE Transactions on Network and Service Management, vol. 17, no. 2, pp. 1000-1012, June 2020, doi: 10.1109/TNSM.2020.2985080.
我们提出了一种风险感知计算卸载（RCO）策略
In this paper, we propose a risk-aware computation offloading (RCO) policy
1我们为支持MEC的小型蜂窝网络设计了风险感知计算分流（RCO）。它共同考虑了服务器端攻击所引起的服务延迟和安全风险。
2基于StackelbergGame（边缘系统运营商为领导者，攻击者为追随者），提出了RCO问题，同时考虑了边缘系统运营商和运营商的战略行为。为了应对攻击者行为的不确定性，我们使用贝叶斯Stackelberg游戏框架，在该框架中，边缘运营商无需确切了解其面临的攻击者.
3为了促进推导RCO的Stackelberg平衡，我们提出了两种修剪策略：启发式规则（HP）和分支界限（BaB）。惠普通过分析可能的攻击者类型，用户需求分布和用户边缘可访问性来排除非均衡策略。 BaBuse进行分离式编程，并通过Bender的裁剪以分支和边界的方式创建搜索树。

1. We design a Risk-aware Computation Offloading (RCO)for MEC-enabled small-cell networks. It jointly considersthe service delay and security risk caused by server-sideattacks. The proposed method is cost-efficient and suitable forimmediate deployment.2) The RCO problem is formulated based on the StackelbergGame (the edge system operator acts as the leader and theattacker acts as the follower) by considering the strategicbehavior of both the edge system operator and attackers.To deal with the uncertainty in attackers’ behavior, we usethe Bayesian Stackelberg Game framework where the edgeoperator does not need to know precisely the attacker it faces.3) To facilitate the derivation of the Stackelberg equilibriumof RCO, we propose two pruning strategies: Heuristic Rules(HP) and Branch-and-Bound (BaB). HP works by analyzingpossible attacker types, user demand distribution, and user-edge accessibility to rule out non-equilibrium strategies. BaBuses disjunctive programming and Bender’s cut to create asearch tree by branch-and-bound.4) We run extensive simulations to evaluate the performanceof RCO under various system configurations. The result con-firms that RCO significantly improves the security of MECsystems and the Stackelberg equilibrium can be derived moreefficiently compared to the existing approaches.The rest of this paper is organized as follows. Section IIreviews related works. Section III gives the system modeland problem formulation. Section IV formulates RCO as aStackelberg game and proposes two pruning strategies forderiving the equilibrium. Section VI carries out simulations,followed by conclusions in Section VII.
   Energy-Efficient Computation Offloading for Secure UAV-Edge-Computing Systems
   T. Bai, J. Wang, Y. Ren and L. Hanzo, “Energy-Efficient Computation Offloading for Secure UAV-Edge-Computing Systems,” in IEEE Transactions on Vehicular Technology, vol. 68, no. 6, pp. 6074-6087, June 2019, doi: 10.1109/TVT.2019.2912227.
   安全能源效率问题的求解我们建立UMEC建立了一个包括无人机、APA和窃听器的安全模型，并给出了在存在主动窃听器的情况下，受持续时间和安全约束的节能计算卸载问题，固定位置的被动窃听器和随机位置的被动窃听器
   Energy-efficiency problem formulation for secure UMEC:We establish a secure model including a UAV, an APas well as an eavesdropper, and formulate an energy-efficient computation offloading problem, subject to bothtime-duration and security constraints, in the presence ofan active eavesdropper, a passive eavesdropper at a fixedlocation and a passive eavesdropper at a random location

嵌入式安全任务卸载模型
Security Embedded Offloading Requirements for IoT-Fog Paradigm
S. U. Jamil, M. A. Khan and M. Ali, “Security Embedded Offloading Requirements for IoT-Fog Paradigm,” 2019 IEEE Microwave Theory and Techniques in Wireless Communications (MTTW), Riga, Latvia, 2019, pp. 47-51, doi: 10.1109/MTTW.2019.8897219.
我们提出了使用IoT-Fog的嵌入式安全任务卸载模型的概念框架 范例。
We describe various criteria based on its security impli-cation used in recently available middleware technologiesduring secure offloading from IoT devices to more securecomputing environment i.e, fog or cloud.•We present a conceptual framework for embedded secu-rity task offloading model using IoT-Fog paradigm. Weargue that such model can play a crucial role in futurewireless networks.•We present a review of the middle-ware and enablingtechnologies and its security features useful in differentfog,cloud and IoT architectures.•We enlist some of the research opportunities to improvesecure task offloading from IoT into fog computing. Wefocused on solutions based on available criteria, enablingtechnologies and middle-ware technologies
针对随机干扰的SAVE-S算法
Secure Edge Computing in IoT via Online Learning
B. Li, T. Chen, X. Wang and G. B. Giannakis, “Secure Edge Computing in IoT via Online Learning,” 2018 52nd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2018, pp. 2149-2153, doi: 10.1109/ACSSC.2018.8645223.
利用MAB框架，我们开发了一种新的SAVE-S算法来实现安全边缘计算下的突发干扰攻击。SAVE-S能够融合相邻节点间的信息共享，保证边缘计算的安全性。
Leveraging MAB framework, we develop a novel SAVE-S algorithm to achieve secure edge computing understochastic jamming attacks. It is also shown that SAVE-S is capable of incorporating the information sharingamong neighbor nodes to ensure more secure edge com-puting.
Security Energy Efficiency Maximization for Untrusted Relay Assisted NOMA-MEC Network With WPT
P. Zhao, W. Zhao, H. Bao and B. Li, “Security Energy Efficiency Maximization for Untrusted Relay Assisted NOMA-MEC Network With WPT,” in IEEE Access, vol. 8, pp. 147387-147398, 2020, doi: 10.1109/ACCESS.2020.3015786.
我们研究了NOMA-MEC系统的安全性能。在卸载过程中考虑了目的地辅助干扰以防止信息泄漏。
• we study the security performance of the NOMA-MEC system. And destination-assisted jamming is considered to prevent the leakage of information during the offloading process.
仿真结果表明，中继采用目的地辅助干扰后能够实现安全传输，采用目的地辅助干扰的安全能量效率明显优于不采用目的地辅助干扰的安全能量效率。结果表明，NOMA传输的安全能量效率优于OMA传输。
• The simulation results show that the relay can achieve security transmission after taking destination-assisted jamming and the security energy efficiency of taking destination-assisted jamming is significantly better than that without taking destination-assisted jamming. It also shows that the security energy efficiency of NOMA transmission is better than OMA transmission.

Optimal Security-Aware Virtual Machine Management for Mobile Edge Computing Over 5G Networks
G. H. S. Carvalho, I. Woungang, A. Anpalagan and I. Traore, “Optimal Security-Aware Virtual Machine Management for Mobile Edge Computing Over 5G Networks,” in IEEE Systems Journal, doi: 10.1109/JSYST.2020.3005201.
在本文中，我们使用半马尔可夫决策流程框架制定了一种安全的虚拟机管理（VMM）机制，旨在共同降低服务拒绝和安全风险，同时以分散的方式满足对延迟敏感的应用程序的位置感知要求。提出了一种新的度量标准，即“平均安全风险”，以量化考虑到的用于执行和保护虚拟机（VM）数量的卸载应用程序的感知风险。
In this article, we formulate a secure virtualmachine management (VMM) mechanism using the semi-Markovdecision process framework that seeks to jointly minimize theservice rejection and the security risk, while meeting the loca-tion awareness requirements of latency-sensitive applications in adecentralized fashion. A new metric called mean security risk isproposed to quantify the perceived risk of an offloaded applicationconsidering the number of virtual machines (VMs) that is used toexecute and to protect it.
Secure and Optimized Load Balancing for Multi-Tier IoT and Edge-Cloud Computing Systems
W. -Z. Zhang et al., “Secure and Optimized Load Balancing for Multi-Tier IoT and Edge-Cloud Computing Systems,” in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2020.3042433.
因此，在本研究中，除了提出MEC系统的联合负载平衡和计算卸载技术外，我们还引入了一个新的安全层来规避潜在的安全问题。首先，提出了一种在sbs间实现mdu有效再分配的负载均衡算法。此外，提出了一种新的高级加密标准（AES）加密技术，该加密技术采用基于心电图（ECG）信号的加解密密钥作为安全层，以保护数据在传输过程中的脆弱性。在此基础上，以降低系统的时间和能量需求为目标，建立了一个负载平衡、计算卸载和安全性的集成模型。
Therefore, in this study, in addition to proposing a joint load balancing and computation offloading technique for MEC systems, we introduce a new security layer to circumvent potential security issues. First, a load balancing algorithm for efficient redistribution of MDUs among sBSs is proposed. In addition, a new advanced encryption standard (AES) cryptographic technique suffused with electrocardiogram (ECG) signal-based encryption and decryption key is presented as a security layer to safeguard the vulnerability of data during the transmission. Furthermore, an integrated model of load balancing, computation offloading and security is formulated as a problem whose goal is to decrease the time and energy demands of the system. Detailed experimental results prove that our model with and without the additional security layers can save about 68.2% and 72.4% of system consumption compared to the local execution.
添加安全层
Efficient and Secure Multi-User Multi-Task Computation Offloading for Mobile-Edge Computing in Mobile IoT Networks
I. A. Elgendy, W. -Z. Zhang, Y. Zeng, H. He, Y. -C. Tian and Y. Yang, “Efficient and Secure Multi-User Multi-Task Computation Offloading for Mobile-Edge Computing in Mobile IoT Networks,” in IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2410-2422, Dec. 2020, doi: 10.1109/TNSM.2020.3020249. I. A. Elgendy, W. -Z. Zhang, Y. Zeng, H. He, Y. -C. Tian and Y. Yang, “Efficient and Secure Multi-User Multi-Task Computation Offloading for Mobile-Edge Computing in Mobile IoT Networks,” in IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2410-2422, Dec. 2020, doi: 10.1109/TNSM.2020.3020249.
Ibrahim A. Elgendy; Wei-Zhe Zhang; Yiming Zeng; Hui He; Yu-Chu Tian; Yuanyuan Yang
Published in: IEEE Transactions on Network and Service Management ( Volume: 17, Issue: 4, Dec. 2020)
在将物联网应用程序的数据传输到MEC服务器之前，将安全层添加到MEC卸载中，以保护物联网应用程序的数据免受网络攻击。
A security layer is added into the MEC offloading toprotect the data of IoT applications from cyber-attacksbefore the data are transferred to the MEC server.

保密中断概率来衡量
Energy-Efficient Secure NOMA-Enabled Mobile Edge Computing Networks
W. Wu, F. Zhou, P. Li, P. Deng, B. Wang and V. C. M. Leung, “Energy-Efficient Secure NOMA-Enabled Mobile Edge Computing Networks,” ICC 2019 - 2019 IEEE International Conference on Communications (ICC), Shanghai, China, 2019, pp. 1-6, doi: 10.1109/ICC.2019.8761823.
DOI: 10.1109/ICC.2019.8761823
Wei Wu; Fuhui Zhou; Pei Li; Ping Deng; Baoyun Wang; Victor C. M. Leung
Published in: ICC 2019 - 2019 IEEE International Conference on Communications (ICC)
考虑实际的被动窃听场景，采用保密中断概率来衡量负载计算的保密性能。在这种情况下，我们研究了在负载率保密性约束、计算延迟约束和保密中断概率约束下，使所有用户的加权和能耗最小的问题，得到了该问题的半封闭解。
The secrecy outage probability is adopted to measure the secrecy performance of computation ofloading by considering the practically passive eavesdropping scenario. Under this setup, we investigate the problem of minimizing the weighted sum-energy consumption for all users, subject to the secrecy ofloading rates constraints, the computation latency constraints and the secrecy outage probability constraints, and then derive the semi-closed form solution for this problem. Numerical results are provided and demonstrate that the merits of our proposed design are better than those of the alternative benchmark schemes.
基于区块链
A Reinforcement Learning and Blockchain-Based Trust Mechanism for Edge Networks
L. Xiao et al., “A Reinforcement Learning and Blockchain-Based Trust Mechanism for Edge Networks,” in IEEE Transactions on Communications, vol. 68, no. 9, pp. 5460-5470, Sept. 2020, doi: 10.1109/TCOMM.2020.2995371.
Published in: IEEE Transactions on Communications ( Volume: 68, Issue: 9, Sept. 2020)
DOI: 10.1109/TCOMM.2020.2995371
Liang Xiao; Yuzhen Ding; Donghua Jiang; Jinhao Huang; Dongming Wang; Jie Li; H. Vincent Poor
我们提出了一种基于区块链的MEC信任机制来抑制自私边缘设备的攻击动机，同时解决了自私边缘攻击和伪造服务记录攻击针对支持深度学习的边缘节点，提出了进一步提高计算性能的算法。
We formulate a blockchain based MEC trust mechanismto suppress the attack motivation of selfish edge devicesand address both selfish edge attacks and faked servicerecord attacks.•We propose a RL based edge CPU allocation algorithmto optimize the number of CPUs for the offloading task.A DRL based CPU allocation algorithm is also presentedfor the edge nodes that support deep learning to furtherimprove the computational performance.•We analyze the computational complexity of the pro-posed scheme and provide the convergence utility for theedge node, which is verified via experimental results.