Security Enhancement for Mobile Edge Computing Through Physical Layer Authentication

Abstract

In this paper, we investigate the security threats in mobile edge computing (MEC) of Internet of things, and propose a deep-learning (DL)-based physical (PHY) layer authentication scheme which exploits channel state information (CSI) to enhance the security of MEC system via detecting spoofing attacks in wireless networks. Moreover, three gradient descent algorithms are adopted to accelerate the training of deep neural networks, which enables smaller computation overheads and lower energy consumptions. In addition, the maximum likelihood function of multi-user authentication method is derived, which explains why cross entropy is chosen as the loss function. The vectorization cost function is also derived. The mini batch scheme and 2 regularization are adopted to improve training accuracy and avoid over-fitting, respectively. Moreover, the simulation and experimental results show that the DL-based PHY-layer authentication approaches can distinguish multiple legitimate edge nodes from malicious nodes and attacker by CSIs, effectively. Our proposed method supports a better performance compared with the traditional hypothesis test based method.INDEX TERMS Mobile edge computing (MEC), the Internet of things (IoT), PHY-layer authentication, deep neural network (DNN), multi-user.

A Framework for Off-Line Operation of Smart and Traditional Devices of IoT Services

“…In an IoT scenario, edge computing provides computational power, secures access to the edge data, reduces latency for time-sensitive applications, supports performance in low-bandwidth environments and eases overall network congestion [ 25 ]. In this way, merging multiple end devices into a single module can significantly reduce the calculation amount of the end device, and edge computing can be implemented [ 6 , 7 , 13 , 14 , 15 , 16 , 17 , 18 ].…”

“…In past research, edge computing was implemented to ensure the reliability in local, and the communication latency reduced [ 6 , 7 , 13 , 14 , 15 , 16 , 17 , 18 ]. However, in these works of literature, most of them are assisted by an additional device server; this is an additional overhead to the hardware cost and should consider whether it is necessary, for example, Smart Farm, where communication of the network is poor.…”

“…Therefore, this study moves the essential functions of IoT applications to the gateway. Compared with [ 6 , 7 , 13 , 18 ] and this study, it is feasible to use the more substantial computing power of the gateway to perform edge computing to assist other end devices to compute. Then, edge devices can not only transmit data but also preprocess data and analyse real-time data, which can support edge computing and provide logic control services.…”

“…However, the huge amount of calculations involved in edge computing cannot be used in IoT devices with a low calculation capacity and storage space and large power consumption. Therefore, in a smart home, smart grid or smart city environment, the local device transmits data to the gateway via wireless communication, i.e., edge computing implemented through the computing capabilities of gateways [ 13 , 14 , 15 , 16 , 17 , 18 ]. In addition, the introduction of boundary computing into the IoT system increases the reliability of the IoT system.…”

Secure and Efficient Image Cryptography Technique using Choas and DNA Encoding Methodology

“…This process of encryption can be described as asymmetric and symmetric depending on the key usage. In detail, the asymmetric method of encryption is essential to complete the process by using a public key [3] and in pertaining to the SKE (Symmetric Key Encryption) the common key will be exchanged among the transceiver nodes. When compared between both the kind of encryption techniques, SKE criteria is found to be effective, simple, and faster for the macro image size, but the key management is crucial for SKE, as the key among the sender and receiver need to be safely communicated in the communication system defending with the untrusted intruder [7,8,9].…”