Showing papers by "Zheng Yan published in 2023"

Efficient Spectral Graph Convolutional Network Deployment on Memristive Crossbars

Abstract: Graph Neural Networks (GNNs) have attracted increasing research interest for their remarkable capability to model graph-structured knowledge. However, GNNs suffer from intensive data exchange and poor data locality, which will cause critical performance and energy bottlenecks under conventional complementary metal oxide semiconductor (CMOS)-based von-Neumann computing architectures (graphics processing unit (GPU), central processing unit (CPU)) for the “Memory Wall” issue. Fortunately, memristive crossbar-based computation has emerged as one of the most promising neuromorphic computing architectures, which has been widely studied as the computing platform for convolutional neural network (CNNs), recurrent neural network (RNNs), spiking neural network (SNNs), etc. This paper proposes the deployment of spectral graph convolutional networks (GCNs) on memristive crossbars. Further, based on the structure of GCNs (extremely high sparsity and unbalanced non-zero data distribution) and the neuromorphic characteristics of memristive crossbar circuit, we propose the acceleration method that consists of Sparse Laplace Matrix Reordering and Diagonal Block Matrix Multiplication. The simulated experiment on memristor crossbars achieves 90.3% overall accuracy on the supervised learning graph dataset (QM7), and compared with the original computation, the proposed acceleration computing framework (with half-size diagonal blocks) achieves a 27.3% reduction of memristor number. Additionally, on the unsupervised learning dataset (Karate club), our method shows no loss of accuracy with half-size diagonal block mapping and reaches a 32.2% reduction of memristor number.

Physical Model Informed Fault Detection and Diagnosis of Air Handling Units Based on Transformer Generative Adversarial Network

Abstract: Physics theory integrated machine learning models enhance the interpretability and performance of artificial intelligence (AI) techniques to real-world industrial applications, such as the fault detection and diagnosis (FDD) of air handling units (AHU). Traditional machine learning-based automated FDD model demonstrates a high classification accuracy with sufficient training data samples, however, suffers from physical interpretation of the machine learning models. In this article, a physical model integrated Wasserstain generative adversarial network (WGAN) model is presented for AHU FDD with a scenario of insufficient training data samples. The proposed solution tackles the real-world problem of AHU FDD and enhances the model interpretability significantly. A transformer-WGAN model is designed to further improve the proposed FDD framework. Experimental results show that the proposed method outperforms existing AHU FDD methods with imbalanced real-world training data samples.

DePTVM: Decentralized Pseudonym and Trust Value Management for Integrated Networks

Abstract: Evaluating and sharing user equipment (UE) trust across multiple network domains can greatly support security and trust management of future integrated heterogeneous networks. But the dilemma between identity privacy preservation and trust evaluation efficacy causes a big challenge in pseudonym and trust value management. Most existing approaches either rely on a trusted third party (TTP) and non-collusive parties, or deploy trusted execution environments (TEEs). They cannot be applied directly into a trustless heterogeneous network environment, where network domains do not trust with each other and it is hard to setup a fully trusted party. In this paper, we propose DePTVM, a decentralized pseudonym and trust value management scheme for integrated heterogeneous networks, where different network operators jointly maintain a list of $< $ pseudonym, trust value $>$ pairs by employing verifiable shuffling and trust obfuscation based on blockchain in order to support anonymous trust evaluation and ensure pseudonym unlinkability. We analyze DePTVM with respect to correctness, unforgeability, anonymity and unlinkability, and evaluate its performance through simulations. Experimental results show that trust synchronization can be achieved across domains within 9 seconds with our experimental settings and the time taken by the most complex operation (i.e., verifiable shuffling) of operator agent increases linearly with the scale of maintained list. Analysis and experimental results imply DePTVM's potential in practical applications.

A Survey on Blockchain-Based Trust Management for Internet of Things

Abstract: Internet of Things (IoT) aims to create a vast network with billions of things that can seamlessly create and exchange data, establishing intelligent interactions between people and objects around them. It is characterized with openness, heterogeneity, and dynamicity, which inevitably introduce severe security, privacy, and trust issues that hinder the widespread application of IoT. Trust management (TM) holds great promise in identifying malicious nodes, maintaining trust relationships, and enhancing system security. Traditional TM systems (TMSs) can be classified into centralized, semi-centralized, and distributed ones, all three of which suffer from critical challenges and thus are not sufficient for facilitating IoT development. Blockchain, as a disruptive technology, can help addressing the challenges of TM in IoT, thanks to its advanced features, such as decentralization, consistency, and tamper-proofing. As a result, blockchain-based TM (BC-TM) has been extensively studied in recent years to achieve decentralized TM in IoT. However, it still lacks a comprehensive survey on the current state of the arts. To fill this gap, in this article, we conduct a serious survey on BC-TM in IoT. We first propose a set of evaluation criteria that should be met by a TMS in IoT. Then, we propose a taxonomy of TMSs and continue with a thorough review on BC-TM in IoT by employing the proposed criteria. In the end, based on the review, a series of open issues are identified, and future research directions are suggested.

XAuth: Secure and Privacy-Preserving Cross-Domain Handover Authentication for 5G HetNets

Abstract: Fifth generation (5G) networks are highly heterogeneous, with ultradense base stations (BSs), due to the low penetration of millimeter waves and the availability of different access technologies. However, the continuous heterogeneity and densification of 5G networks pose great challenges to network security, especially for user mobility support. In the process of user handover between BSs or between different network domains, user access authentication and security session establishment are far riskier compared to 4G networks. On the one hand, the overhead of handover authentication increases significantly as handovers become more frequent in an ultradense network. On the other hand, the differentiation of security schemes in heterogeneous networks (HetNets) poses a big challenge to handover authentication. Successfully designing a secure, privacy preserving, and efficient handover authentication protocol for heterogeneous and ultradense 5G networks would substantially expand the prospects of future 5G network applications. Although numerous solutions (e.g., challenge-response-based, public key cryptography-based, physical-layer information-based, and blockchain-based solutions) have been proposed to solve the cross-domain handover authentication problem, most of them surfer from security and privacy vulnerabilities and unreasonable performance overhead. In this article, we propose XAuth, a secure and privacy-preserving authentication protocol for both intradomain and interdomain handover in 5G HetNets based on blockchain. The proposed protocol can achieve mutual authentication, key agreement between user equipment (UE) and target network, and is characterized by forward secrecy, backward secrecy, user anonymity, and conditional privacy preservation. Formal security analysis and comprehensive performance evaluation demonstrate the security and effectiveness of the proposed protocol.

Hierarchical Central-Local Inverter-Based Voltage Control in Distribution Networks Considering Stochastic PV Power Admissible Range

Abstract: This paper proposes a hierarchical distribution network voltage control method considering active and reactive power coordination of PV units in both central and local control stages. In contrast to the traditional local control methods, the proposed method defines the admissible range (AR) of PV power and determines it via centralized optimization to realize active PV power curtailments in the local control stage. The affine decision rule (ADR) is adopted to control the reactive power with respect to active power within AR. A distributionally robust chance constraint is designed, based on statistical indices of active PV power, to assess the probability that active PV power generation would fall inside AR. A two-stage optimization problem that can simultaneously provide central and local control strategies is proposed, which is transformed into tractable formulas based on the Gauss Inequality as well as ADR and binary expansion techniques. The proposed method solutions are compared with those of the theoretically optimal method, a robust central-local control method, and a local control method to show the value of hierarchical inverter control with AR in reducing PV power curtailment and ensuring nodal voltages within limits.

Security Analysis of Triangle Channel-Based Physical Layer Key Generation in Wireless Backscatter Communications

Abstract: Ambient backscatter communication (AmBC) enables ultra-low-power communications by backscattering ambient radio frequency (RF) signals and harvesting energy simultaneously. It has emerged as a cutting-edge technology for supporting a variety of Internet of Things (IoT) applications. However, existing research lacks effective secret key sharing schemes for safeguarding communications between resource-constrained backscatter devices (BDs) in AmBC systems. In this paper, we present, Tri-Channel, a novel physical layer key generation scheme between two BDs by multiplying downlink signals and backscatter signals to obtain the information of a triangle channel as a shared random secret source for key generation. In particular, we analyze the security of our scheme under both passive and active attacks, concretely Eavesdropping Attack (EA), Control Channel Attack (CCA), Signal Manipulative Attack (SMA), and Untrusted RF-Source Attack (URSA). Through theoretical analysis and simulations by comparing with a traditional scheme (named Tradi-Channel), we found that our scheme consistently outperforms the Tradi-Channel under the EA and two active attacks (CCA and SMA). In addition, it shows better security performance under URSA, which is proposed based on the unauthenticated characteristic of BDs in Tri-Channel, even though URSA is more vital than SMA. Concretely, Tri-Channel’s secret key rate (SKR) outperforms Tradi-Channel’s under the above four passive and active attacks. This implies that our scheme is advanced in terms of both security and efficiency of key generation. Numerous extensive simulations further prove our theoretical analysis results.

A survey on blockchain sharding.

Abstract: As a promising technology, blockchain has found widespread application in numerous decentralized systems. However, the scalability problem of blockchain has drawn considerable criticism. Sharding, an effective technology, offers a solution to enhance blockchain scalability by enabling parallel validation and confirmation of transactions or new block generation. Although extensive research has been conducted on sharding, the existing literature still lacks a thorough review on its current state of arts with comprehensive analysis and evaluation. In this paper, we propose a series of evaluation criteria regarding scalability, applicablity, and reliability. Additionally, we classify the cutting-edge sharding schemes based on blockchain type and sharding techniques. We then provide a comprehensive overview of these existing schemes by analyzing their respective advantages and disadvantages according to the proposed criteria. At the end of the survey, we highlight open issues and suggest future research directions based on the results of our meticulous analysis.

A Survey on the Control Lyapunov Function and Control Barrier Function for Nonlinear-Affine Control Systems

Abstract: This survey provides a brief overview on the control Lyapunov function (CLF) and control barrier function (CBF) for general nonlinear-affine control systems. The problem of control is formulated as an optimization problem where the optimal control policy is derived by solving a constrained quadratic programming (QP) problem. The CLF and CBF respectively characterize the stability objective and the safety objective for the nonlinear control systems. These objectives imply important properties including controllability, convergence, and robustness of control problems. Under this framework, optimal control corresponds to the minimal solution to a constrained QP problem. When uncertainties are explicitly considered, the setting of the CLF and CBF is proposed to study the input-to-state stability and input-to-state safety and to analyze the effect of disturbances. The recent theoretic progress and novel applications of CLF and CBF are systematically reviewed and discussed in this paper. Finally, we provide research directions that are significant for the advance of knowledge in this area.

Decentralized P2P Federated Learning for Privacy-Preserving and Resilient Mobile Robotic Systems

Abstract: Swarms of mobile robots are being widely applied for complex tasks in various practical scenarios toward modern smart industry. Federated learning (FL) has been developed as a promising privacy-preserving paradigm to tackle distributed machine learning tasks for mobile robotic systems in 5G and beyond networks. However, unstable wireless network conditions of the complex and harsh working environment may lead to poor communication quality and bring big challenges to traditional centralized global training in FL models. In this article, a Peer-to-Peer (P2P) based Privacy-Perceiving Asynchronous Federated Learning (PPAFL) framework is introduced to realize the decentralized model training for secure and resilient modern mobile robotic systems in 5G and beyond networks. Specifically, a reputation-aware coordination mechanism is designed and addressed to coordinate a group of smart devices dynamically into a virtual cluster, in which the asynchronous model aggregation is conducted in a decentralized P2P manner. A secret sharing based communication mechanism is developed to ensure an encrypted P2P FL process, while a Secure Stochastic Gradient Descent (SSGD) scheme is integrated with an Autoencoder and a Gaussian mechanism is developed to ensure an anonymized local model update, communicating within a few neighboring clients. The case study based experiment and evaluation in three different application scenarios demonstrate that the PPAFL can effectively improve the security and resilience issues compared with the traditional centralized approaches for smart mobile robotic applications in 5G and beyond networks.

A Survey on Cross-chain Technologies

Abstract: Blockchain has attracted more and more attention of academia, industry and government in recent decade. Different usage demands have inspired various blockchain designs, forming different blockchain systems, which however leads to information islands. Many cross-chain technologies have been proposed to link different blockchains together and expand the utility of blockchain. Nevertheless, the cross-chain technology is still in its infancy, which faces many problems that retard its wide application, for example, the issues related to security, privacy and effectiveness. In order to further investigate cross-chain technologies, it is essential to understand its current state of arts. Although there are some surveys about cross-chain technologies driven by specific demands, the literature still lacks a comprehensive survey focusing on security, privacy and effectiveness of cross-chain technologies. In this paper, we provide a review on existing cross-chain technologies based on a comprehensive set of criteria on security, privacy and other performance. We first propose a blockchain interoperability architecture for the purpose of analyzing potential threats and problems regarding security, privacy and effectiveness. We then summarize a set of criteria regarding these quality attributes. Next, we comprehensively review the representative works on cross-chain technologies according to a taxonomy based on applied types of techniques and cross-chain purposes. In each work review, we provide a serious discussion on its pros and cons by employing our proposed criteria. Finally, based on our review and analysis, we figure out a number of open issues and step ahead to direct future research directions on cross-chain technologies.

LiVoAuth: Liveness Detection in Voiceprint Authentication With Random Challenges and Detection Modes

Abstract: Voiceprint authentication provides great convenience to users in many application scenarios. However, it easily suffers from spoofing attacks including speech synthesis, speech conversion, and speech replay. Liveness detection is an effective way to resist these attacks. But existing methods suffer from many disadvantages, such as extra deployment costs due to precise data collection, environmental disturbance, high computational overhead, and operational complexity. A uniform platform that can offer voiceprint authentication as a service (VAaS) over the cloud is also lacked. Hence, it is imperative to design an economic and effective method for liveness detection in voiceprint authentication. In this article, we propose a novel liveness detection method named LiVoAuth for voiceprint authentication. It applies a randomly generated vector sequence as liveness detection mode (LDM), corresponding to a random challenge code used for authentication. We implement LiVoAuth and conduct a series of user studies to evaluate its performance in terms of accuracy, stability, efficiency, security, and user acceptance. Experimental results demonstrate its advantages compared with cutting-edge methods

Taxonomy and Recent Advance of Game Theoretical Approaches in Adversarial Machine Learning: A Survey

Abstract: Carefully perturbing adversarial inputs degrades the performance of traditional machine learning (ML) models. Adversarial machine learning (AML) that takes adversaries into account during training and learning emerges as a valid technique to defend against attacks. Due to the complexity and uncertainty of adversaries’ attack strategies, researchers utilize game theory to study the interactions between an adversary and an ML system designer. By configuring different game rules and analyzing game outcomes in an adversarial game, it is possible to effectively predict attack strategies and to produce optimal defense strategies for the system designer. However, the literature still lacks a holistic review of adversarial games in AML. In this paper, we extend the scope of previous surveys and provide a thorough overview of existing game theoretical approaches in AML for adaptively defending against adversarial attacks. For evaluating these approaches, we propose a set of metrics to discuss their merits and drawbacks. Finally, based on our literature review and analysis, we raise several open problems and suggest interesting research directions worthy of special investigation.

Routing and Scheduling of Mobile Energy Storage System for Electricity Arbitrage Based on Two-Layer Deep Reinforcement Learning

Abstract: The mobile energy storage system (MESS) plays an increasingly important role in energy systems because of its spatial and temporal flexibilities, while the high upfront investment cost requires developing corresponding operation and arbitrage strategies. In the existing literature, the MESS arbitrage problems are usually cast as mixed-integer programming models. However, the performance of this model-based method is deteriorated by the uncertainties of power and transportation networks and the complicated operational characteristics of batteries. To overcome the deficiencies of existing methods, this article proposes a data-driven uncertainty-adaptive MESS arbitrage method considering MESS mobility rules, battery degradation, and operational efficiencies. A two-layer deep reinforcement learning (DRL) method is developed to obtain the discrete mobility and continuous charging or discharging power, and a sequential training strategy is designed to accelerate the convergence of model training. The proposed method is tested using the real-world electricity prices and traffic information of charging stations. Compared with traditional model-based methods that rely on entire and accurate future information, the proposed DRL method obtains high arbitrage profits by learning arbitrage strategies from historical data and making effective decisions with limited real-time information.

Hierarchical Federated Learning With Social Context Clustering-Based Participant Selection for Internet of Medical Things Applications

Abstract: The proliferation in embedded and communication technologies made the concept of the Internet of Medical Things (IoMT) a reality. Individuals’ physical and physiological status can be constantly monitored, and numerous data can be collected through wearable and mobile devices. However, the silo of individual data brings limitations to existing machine learning approaches to correctly identify a user’s health status. Distributed machine learning paradigms, such as federated learning, offer a potential solution for privacy-preserving knowledge sharing without sending raw personal data. However, federated learning is vulnerable to harmful participants that can degrade the overall model quality by sharing low-quality data. Therefore, it is critical to select suitable participants to ensure the accuracy and efficiency of federated learning. In this article, a unique clustering-based approach is proposed to use social context data for participant selection. Different edge participant groups will be established, and group-specific federated learning will be performed. The models of various edge groups will be further aggregated to strengthen the robustness of the global model. The experimental results demonstrated that through participant selection, clustering-based hierarchical federated learning can achieve better results with less participants in two different IoMT applications for ECG and human motion monitoring. This shows the efficacy of the proposed method in improving federated learning performance and efficiency in various IoMT applications.

Disentangling Stochastic PDE Dynamics for Unsupervised Video Prediction.

Abstract: Unsupervised video prediction aims to predict future outcomes based on the observed video frames, thus removing the need for supervisory annotations. This research task has been argued as a key component of intelligent decision-making systems, as it presents the potential capacities of modeling the underlying patterns of videos. Essentially, the challenge of video prediction is to effectively model the complex spatiotemporal and often uncertain dynamics of high-dimensional video data. In this context, an appealing way of modeling spatiotemporal dynamics is to explore prior physical knowledge, such as partial differential equations (PDEs). In this article, considering real-world video data as a partly observed stochastic environment, we introduce a new stochastic PDE predictor (SPDE-predictor), which models the spatiotemporal dynamics by approximating a generalized form of PDEs while dealing with the stochasticity. A second contribution is that we disentangle the high-dimensional video prediction into low-level dimensional factors of variations: time-varying stochastic PDE dynamics and time-invariant content factors. Extensive experiments on four various video datasets show that SPDE video prediction model (SPDE-VP) outperforms both deterministic and stochastic state-of-the-art methods. Ablation studies highlight our superiority driven by both PDE dynamics modeling and disentangled representation learning and their relevance in long-term video prediction.

TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support

Abstract: Trust evaluation assesses trust relationships between entities and facilitates decision-making. Machine Learning (ML) shows great potential for trust evaluation owing to its learning capabilities. In recent years, Graph Neural Networks (GNNs), as a new ML paradigm, have demonstrated superiority in dealing with graph data. This has motivated researchers to explore their use in trust evaluation, as trust relationships among entities can be modeled as a graph. However, current trust evaluation methods that employ GNNs fail to fully satisfy the dynamicity nature of trust, overlook the adverse effects of attacks on trust evaluation, and cannot provide convincing explanations on evaluation results. To address these problems, in this paper, we propose TrustGuard, a GNN-based accurate trust evaluation model that supports trust dynamicity, is robust against typical attacks, and provides explanations through visualization. Specifically, TrustGuard is designed with a layered architecture that contains a snapshot input layer, a spatial aggregation layer, a temporal aggregation layer, and a prediction layer. Among them, the spatial aggregation layer can be plugged into a defense mechanism for a robust aggregation of local trust relationships, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns. Extensive experiments on two real-world datasets show that TrustGuard outperforms state-of-the-art GNN-based trust evaluation models with respect to trust prediction across single-timeslot and multi-timeslot, even in the presence of attacks. In particular, TrustGuard can explain its evaluation results by visualizing both spatial and temporal views.

A Deep Learning-Based Indoor Odor Compass

Abstract: Mobile robot-based odor source localization (OSL) has broad applications in various industrial and daily-life scenarios. To this end, a deep learning-based odor compass is designed in this work. Functionally, the designed odor compass is divided into three primary modules, which are the sensing module (i.e., a sensor array composed of four metal-oxide-semiconductor (MOS) gas sensors), the communication module, and the remote data processing module (i.e., a deep learning-based algorithm). In particular, a deep learning-based odor attention (DL-OA) model is proposed to realize an end-to-end odor source direction estimation (OSDE) based on the responses of gas sensor array. Moreover, the proposed DL-OA model adopts a separated spatial-temporal attention-based encoder-decoder structure. Furthermore, the average validation error in estimating the OSD in an indoor environment is 4.98°, essentially demonstrating the effectiveness of designed odor compass.

Coordinated Optimization of Emergency Response Resources in Transportation-Power Distribution Networks under Extreme Events

Abstract: The proliferation of electric vehicles (EVs) and the increasing interdependence across power distribution networks (DNs) and transportation networks (TNs) have increased the complexity and vulnerability of the two systems in extreme circumstances. As the interdependence of two infrastructures tightens over time, it is viewed as a dire necessity to strengthen the resilience of the coordinated transportation-power distribution networks (TDNs) against natural disasters. This paper constructs a coordinated optimization method of TN traffic link reversing, DN line switching, and fast charging pile management, to improve the TDN performance in the emergency response stage after disasters. A dynamic TN model and a multi-period DN model are integrated in TDN modeling to capture flow propagations and state variations among time intervals. The coordinated optimization for TDN emergency response is designed as a mixed-integer nonlinear programming (MINLP) problem with high-order objective functions and nonlinear constraints to minimize TN travel costs and DN active and reactive power shortages. An accuracy-aware adaptive piecewise linearization approach combined with Gray code-based encoding is utilized to improve the computational efficiency for solving the TDN optimization problem. Numerical simulations show that the TDN performance is enhanced by coordinating various DN and TN resources, as compared with those of separate and conventional topology controls. The proposed TDN solution method has significantly reduced the computation time for managing extreme conditions while guaranteeing the accuracy of the results as compared with those of the nonlinear model and the linearized model by uniform piecewise linearization.

Robust Parametric Programming for Adaptive Piecewise Linear Control of Photovoltaic Inverters to Regulate Voltages in Power Distribution Systems

Abstract: This paper proposes a robust parametric programming (RPP) method to adaptively obtain piecewise linear control functions of photovoltaic (PV) inverters for real-time voltage regulation in distribution systems. First, the voltage regulation problem is designed as a multi-parameter programming problem, which is transformed into single-parameter linear programming (sp-LP) problems for realizing local control of a PV inverter while considering the maximum voltage deviation caused by other PV units. Second, an alternating iterative algorithm is developed to solve the sp-LP problem of each PV unit and obtain the control functions of all the PV units. Third, considering the information on PV power correlation, a two-level parametric programming problem is established to enhance the voltage regulation performance of PV inverters. A geometric method is developed to solve the inner-level problem, and breakpoint reduction with robust interpolation is developed to improve the computational efficiency in solving the outer-level problem. Four distribution systems integrated with PV units are used to validate the effectiveness of the proposed method. Numerical results show that the performance of the proposed PV inverter control strategy is close to that of the ideal optimal solution and superior to existing piecewise linear control strategies.