In Wireless Sensor Networks (WSNs), when multiple data packets meet during routing to the sink, redundant data can be removed through data fusion, thereby reducing the amount of data transmitted, and increasing the life of the network. However, how to increase the data fusion rate as much as possible and ensure that the delay is lower than the deadline is a challenge issue. To solve this problem, a Differentiated Threshold Configuring joint Optimal Relay Selection based Data Aggregation (DTC-ORS-DA) scheme is proposed, which can significantly reduce redundant data routing and guarantee the delay for WSN. The main innovation is as follow: (1) In DTC-ORS-DA scheme, there are two thresholds: data volume threshold $N_{y}$ and time threshold $T_{y}$ . Data routing can only be performed when $N_{y}$ or $T_{y}$ of the node meet the threshold requirements, so that the data can be fully integrated to minimize the amount of data to be transmitted. More importantly, DTC-ORS-DA adopts differentiated threshold settings based on the characteristics of unbalanced energy consumption in WSNs, and sets a smaller threshold in the far sink area with sufficient energy, so that data packets can be routed quickly. And the near sink area where the energy is tight uses a larger threshold to maximize data fusion, so that the combination can make the data fusion high, the energy is effectively used, and the delay is small. (2) We propose a priority-based relay selection algorithm, which enables child nodes to dynamically select the parent node with the highest priority based on the number of data packets, waiting time, and remaining energy. In the process of routing, the probability of nodes with many data packets or long waiting time being selected as transmission relay is high, which can either increase the data fusion rate or reduce the delay. Finally, the performance comparison with Common data collection Scheme (CS) proves that, the DTC-ORS-DA scheme reduces the average delay by 10.74%-19.91%, increases the life cycle by 9.81% at most, and the energy utilization rate is increased by 6.67%-9.48%.

/pdf/an-efficient-data-aggregation-scheme-based-on-differentiated-3aq2rdx727.pdf

An Efficient Data Aggregation Scheme Based on Differentiated Threshold Configuring Joint Optimal Relay Selection in WSNs

To ensure the security of Internet of Things (IoT) communications, one can use deep packet inspection (DPI) on network middleboxes to detect and mitigate anomalies and suspicious activities in network traffic of IoT, although doing so over encrypted traffic is challenging. Therefore, in this article, an efficient and privacy-preserving encrypted traffic detection scheme is proposed. The scheme uses only lightweight cryptographic operations (i.e., symmetric encryption, hash functions, and pseudorandom functions) to achieve both privacy and security within an inspection round. A dispute resolution mechanism is also designed to address potential disputes between client(s) and server(s). We also present the corresponding security proof and experimental evaluation, which demonstrate that our proposed scheme achieves strong security and privacy preservation and good performance. 

Privacy-Preserving Encrypted Traffic Inspection With Symmetric Cryptographic Techniques in IoT

Integration of Blockchain and Edge Computing in Internet of Things: A Survey

A comparative study of machine learning classifiers for secure RF-PUF-based authentication in internet of things

To ensure the security of Internet of Things (IoT) communications, one can use deep packet inspection (DPI) on network middleboxes to detect and mitigate anomalies and suspicious activities in network traffic of IoT, although doing so over encrypted traffic is challenging. Therefore, in this article, an efficient and privacy-preserving encrypted traffic detection scheme is proposed. The scheme uses only lightweight cryptographic operations (i.e., symmetric encryption, hash functions, and pseudorandom functions) to achieve both privacy and security within an inspection round. A dispute resolution mechanism is also designed to address potential disputes between client(s) and server(s). We also present the corresponding security proof and experimental evaluation, which demonstrate that our proposed scheme achieves strong security and privacy preservation and good performance.

As an emerging technology, industrial Internet of Things (IIoT) connects massive sensors and actuators to empower industrial sectors being smart, autonomous, efficient, and safety. However, due the large number of build-in sensors of IIoT smart devices, the IIoT systems are vulnerable to side-channel attack. In this article, a novel side-channel-based passwords cracking system, namely MAGLeak, is proposed to recognize the victim's passwords by leveraging accelerometer, gyroscope, and magnetometer of IIoT touch-screen smart device. Specifically, an event-driven data collection method is proposed to ensure that the user's keystroke behavior can be reflected accurately by the obtained measurements of three sensors. Moreover, random forest algorithm is leveraged for the recognition module, followed by a data preprocessing process. Extensive experimental results demonstrate that MAGLeak achieves a high recognition accuracy under small training dataset, e.g., achieving recognition accuracy 98% of each single key for 2000 training samples.

MAGLeak: A Learning-Based Side-Channel Attack for Password Recognition With Multiple Sensors in IIoT Environment

Emerging deep neural networks (DNNs) have been emerging in applications (object detection, automatic speech recognition, etc.) deployed on edge devices. To improve the energy efficiency of edge devices, domain specific deep learning accelerators (DLAs) are designed with limited on-chip resources. The manifold DLA designs and evolving DNN topologies bring challenges for applications mapping and scheduling on hardware resources. In this paper, we propose an automatic DNN mapping framework named AutoMap given the hardware backend information. Firstly, a computational graph representation called Extended Directed Weighted Graph (EDWG) is proposed, which realizes unified expression for both spatial and temporal network inter-layer connections. Secondly, an associated partitioner is implemented for splitting an EDWG into subEDWGs, which incorporates the on-chip memory constraint and facilitates weight data reuse on chip. Lastly, a dynamic memory allocation strategy is utilized to alleviate the feature storing burden introduced by the multivarious network sizes and connections. Compared to the baseline mapping methods, experimental results show that our proposed automatic mapping framework can help to speedup the execution of several DNNs on state-of-the-art DLAs, ranging from 1.27x to 3.45x. The utilization of the PE array can increase from 20% to 64%. 

AutoMap: Automatic Mapping of Neural Networks to Deep Learning Accelerators for Edge Devices

Introduction Human emotions vary with temperature factors. However, most studies on emotion recognition based on physiological signals overlook the influence of temperature factors. This article proposes a video induced physiological signal dataset (VEPT) that considers indoor temperature factors to explore the impact of different indoor temperature factors on emotions. Methods This database contains skin current response (GSR) data obtained from 25 subjects at three different indoor temperatures. We selected 25 video clips and 3 temperatures (hot, comfortable, and cold) as motivational materials. Using SVM, LSTM, and ACRNN classification methods, sentiment classification is performed on data under three indoor temperatures to analyze the impact of different temperatures on sentiment. Results The recognition rate of emotion classification under three different indoor temperatures showed that anger and fear had the best recognition effect among the five emotions under hot temperatures, while joy had the worst recognition effect. At a comfortable temperature, joy and calmness have the best recognition effect among the five emotions, while fear and sadness have the worst recognition effect. In cold temperatures, sadness and fear have the best recognition effect among the five emotions, while anger and joy have the worst recognition effect. Discussion This article uses classification to recognize emotions from physiological signals under the three temperatures mentioned above. By comparing the recognition rates of different emotions at three different temperatures, it was found that positive emotions are enhanced at comfortable temperatures, while negative emotions are enhanced at hot and cold temperatures. The experimental results indicate that there is a certain correlation between indoor temperature and physiological emotions.

/pdf/video-elicited-physiological-signal-dataset-considering-1nqfru48.pdf

Video elicited physiological signal dataset considering indoor temperature factors

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in emerging industrial fields such as robotic visions and automobiles. However, current deep learning (DL) faces major challenges for such applications because of the huge computational cost and inefficient learning. Hence, we developed a novel brain-inspired spiking neural network (SNN) based system titled spiking gating flow (SGF) for online action learning. The developed system consists of multiple SGF units which are assembled in a hierarchical manner. A single SGF unit contains three layers: a feature extraction layer, an event-driven layer, and a histogram-based training layer. To demonstrate the capability of the developed system, we employed a standard dynamic vision sensor (DVS) gesture classification as a benchmark. The results indicated that we can achieve 87.5% of accuracy which is comparable with DL, but at a smaller training/inference data number ratio of 1.5:1. Only a single training epoch is required during the learning process. Meanwhile, to the best of our knowledge, this is the highest accuracy among the non-backpropagation based SNNs. Finally, we conclude the few-shot learning (FSL) paradigm of the developed network: 1) a hierarchical structure-based network design involves prior human knowledge; 2) SNNs for content-based global dynamic feature detection.

/pdf/the-spike-gating-flow-a-hierarchical-structure-based-spiking-2zlnovkw.pdf

Zihao Zhao

Papers

MAGLeak: A Learning-Based Side-Channel Attack for Password Recognition With Multiple Sensors in IIoT Environment

AutoMap: Automatic Mapping of Neural Networks to Deep Learning Accelerators for Edge Devices

Video elicited physiological signal dataset considering indoor temperature factors

The spike gating flow: A hierarchical structure-based spiking neural network for online gesture recognition