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 l 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.
Highlights
INTRODUCTIONMobile edge computing (MEC) provides data storage, computing and application services with edge nodes (sensors, smartphones, wearable devices and self-driving cars) and plays an important role in Internet of things (IoT)
Mobile edge computing (MEC) provides data storage, computing and application services with edge nodes and plays an important role in Internet of things (IoT)
DEEP-LEARNING-BASED MULTI-USER AUTHENTICATION Generally speaking, deep neural network (DNN) is a deeper version of artificial neural network (ANN) through increasing the number of hidden layers in order to improve the ability in representation or classification
Summary
Mobile edge computing (MEC) provides data storage, computing and application services with edge nodes (sensors, smartphones, wearable devices and self-driving cars) and plays an important role in Internet of things (IoT). Otoum et al [9] proposed a hierarchical trust-based wireless sensor network (WSN) monitoring model for the smart grid equipment in order to detect the black-hole attack by testing the trade-off between trust and dropped packet ratios for each cluster head (CH). Due to the complexity and variability of channels in practical wireless environments, the PHY-layer authentication schemes, which are based on hypothesis test, cannot distinguish multiple users simultaneously. The proposed deep-learning (DL)-based PHY-layer authentication utilizes spatial heterogeneity of wireless channels It can distinguish multi-users such as legitimate edge nodes, attackers and malicious nodes without a test threshold, which means that the novel methods can adapt to different environments. The elements are represented by the letters or the letters with subscripts and not bold (e.g., nl, L)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
