Showing papers in "IEEE Transactions on Network Science and Engineering in 2021"

BinDaaS: Blockchain-Based Deep-Learning as-a-Service in Healthcare 4.0 Applications

Abstract: Electronic Health Records (EHRs) allows patients to control, share, and manage their health records among family members, friends, and healthcare service providers using an open channel, i.e., Internet. Thus, privacy, confidentiality, and data consistency are major challenges in such an environment. Although, cloud-based EHRs addresses the aforementioned discussions, but these are prone to various malicious attacks, trust management, and non-repudiation among servers. Hence, blockchain-based EHR systems are most popular to create the trust, security, and privacy among healthcare users. Motivated from the aforementioned discussions, we proposes a framework called as Blockchain-Based Deep Learning as-a-Service (BinDaaS). It integrates blockchain and deep-learning techniques for sharing the EHR records among multiple healthcare users and operates in two phases. In the first phase, an authentication and signature scheme is proposed based on lattices-based cryptography to resist collusion attacks among N-1 healthcare authorities from N. In the second phase, Deep Learning as-a-Service (DaaS) is used on stored EHR datasets to predict future diseases based on current indicators and features of patient. The obtained results are compared using various parameters such as accuracy, end-to-end latency, mining time, and computation and communication costs in comparison to the existing state-of-the-art proposals. From the results obtained, it is inferred that BinDaaS outperforms the other existing proposals with respect to the aforementioned parameters.

PPSF: A Privacy-Preserving and Secure Framework Using Blockchain-Based Machine-Learning for IoT-Driven Smart Cities

Abstract: With the evolution of the Internet of Things (IoT), smart cities have become the mainstream of urbanization. IoT networks allow distributed smart devices to collect and process data within smart city infrastructure using an open channel, the Internet. Thus, challenges such as centralization, security, privacy (e.g., performing data poisoning and inference attacks), transparency, scalability, and verifiability limits faster adaptations of smart cities. Motivated by the aforementioned discussions, we present a Privacy-Preserving and Secure Framework (PPSF) for IoT-driven smart cities. The proposed PPSF is based on two key mechanisms: a two-level privacy scheme and an intrusion detection scheme. First, in a two-level privacy scheme, a blockchain module is designed to securely transmit the IoT data and Principal Component Analysis (PCA) technique is applied to transform raw IoT information into a new shape. In the intrusion detection scheme, a Gradient Boosting Anomaly Detector (GBAD) is applied for training and evaluating the proposed two-level privacy scheme based on two IoT network datasets, namely ToN-IoT and BoT-IoT. We also suggest a blockchain-InterPlanetary File System (IPFS) integrated Fog-Cloud architecture to deploy the proposed PPSF framework. Experimental results demonstrate the superiority of the PPSF framework over some recent approaches in blockchain and non-blockchain systems.

CANintelliIDS: Detecting In-Vehicle Intrusion Attacks on a Controller Area Network Using CNN and Attention-Based GRU

Abstract: Controller area network (CAN) is a communication protocol that provides reliable and productive transmission between in-vehicle nodes continuously. CAN bus protocol is broadly utilized standard channel to deliver sequential communications between electronic control units (ECUs) due to simple and reliable in-vehicle communication. Existing studies report how easily an attack can be performed on the CAN bus of in-vehicle due to weak security mechanisms that could lead to system malfunctions. Hence the security of communications inside a vehicle is a latent problem. In this paper, we propose a novel approach named CANintelliIDS, for vehicle intrusion attack detection on the CAN bus. CANintelliIDS is based on a combination of convolutional neural network (CNN) and attention-based gated recurrent unit (GRU) model to detect single intrusion attacks as well as mixed intrusion attacks on a CAN bus. The proposed CANintelliIDS model is evaluated extensively and it achieved a performance gain of 10.79% on test intrusion attacks over existing approaches.

ContractWard: Automated Vulnerability Detection Models for Ethereum Smart Contracts

Abstract: Smart contracts are decentralized applications running on Blockchain. A very large number of smart contracts has been deployed on Ethereum. Meanwhile, security flaws of contracts have led to huge pecuniary losses and destroyed the ecological stability of contract layer on Blockchain. It is thus an emerging yet crucial issue to effectively and efficiently detect vulnerabilities in contracts. Existing detection methods like Oyente and Securify are mainly based on symbolic execution or analysis. These methods are very time-consuming, as the symbolic execution requires the exploration of all executable paths or the analysis of dependency graphs in a contract. In this work, we propose ContractWard to detect vulnerabilities in smart contracts with machine learning techniques. First, we extract bigram features from simplified operation codes of smart contracts. Second, we employ five machine learning algorithms and two sampling algorithms to build the models. ContractWard is evaluated with 49502 real-world smart contracts running on Ethereum. The experimental results demonstrate the effectiveness and efficiency of ContractWard. The predictive Micro-F1 and Macro-F1 of ContractWard are over 96% and the average detection time is 4 seconds on each smart contract when we use XGBoost for training the models and SMOTETomek for balancing the training sets.

B-Ride: Ride Sharing With Privacy-Preservation, Trust and Fair Payment Atop Public Blockchain

Abstract: Ride-sharing is a service that enables drivers to share trips with other riders, contributing to appealing benefits of shared travel cost and reducing traffic congestion. However, the majority of existing ride-sharing services rely on a central third party to organize the service, which make them subject to a single point of failure and privacy disclosure concerns by both internal and external attackers. Moreover, they are vulnerable to distributed denial of service (DDoS) and Sybil attacks launched by malicious users and external attackers. Besides, high service fees are paid to the ride-sharing service provider. In this paper, we propose a decentralized ride-sharing service based on public Blockchain, named B-Ride. B-Ride enables drivers to offer ride-sharing services without relying on a trusted third party. Both riders and drivers can learn whether they can share rides while preserving their trip data, including pick-up/drop-off location, departure/arrival date and travel price. However, malicious users exploit the anonymity provided by the public blockchain to submit multiple ride requests or offers, while not committing to any of them, in order to find a better offer or to make the system unreliable. B-Ride solves this problem by introducing a time-locked deposit protocol for a ride-sharing by leveraging smart contract and zero-knowledge set membership proof. In a nutshell, both a driver and a rider have to show their good will and commitment by sending a deposit to the blockchain. Later, a driver has to prove to the blockchain on the agreed pick-up time that he/she arrived at the pick-up location on time. To preserve rider/driver privacy by hiding the exact pick-up location, the proof is performed using zero-knowledge set membership proof. Moreover, to ensure fair payment, a pay-as-you-drive methodology is introduced based on the elapsed distance of the driver and rider. In addition, we introduce a reputation model to rate drivers based on their past behaviour without involving any third-parties to allow riders to select them based on their history on the system. Finally, we implement our protocol and deploy it in a test net of Ethereum. The experimental results show the applicability of our protocol atop existing real-world blockchains.

BD-VTE: A Novel Baseline Data Based Verifiable Trust Evaluation Scheme for Smart Network Systems

Abstract: Billions of sensors and devices are connecting to the Internet of Thing (IoT) and generating massive data which are benefit for smart network systems. However, low-cost, secure, and efficient data collection from billions of IoT devices in smart city is a huge challenge. Recruiting mobile vehicles (MVs) has been proved to be an effective data collection scheme. However, the previous approaches rarely considered the security. In this paper, a novel Baseline Data based Verifiable Trust Evaluation (BD-VTE) scheme is proposed to guarantee security at a low cost. BD-VTE scheme includes Verifiable Trust Evaluation (VTE) mechanism, Effectiveness-based Incentive (EI) mechanism, and Secondary Path Planning (SPP) strategy, which are respectively used for reliable trust evaluation, reasonable reward, and efficient path adjustment. Among them, an active trust verification mechanism is innovatively proposed in the VTE mechanism, which evaluates the trust of MVs by sending UAVs to perceive IoT devices data as baseline data. This is a fundamental change to the previous passive and unverifiable trust mechanism. The simulation results show that BD-VTE scheme reduces the cost by at least 25.12% ∼ 38.03%, improves the collection rate by 0.91% ∼ 9.65% and increases the accuracy by 10.28% on average compared with the previous strategies.

Learning in the Air: Secure Federated Learning for UAV-Assisted Crowdsensing

Abstract: Unmanned aerial vehicles (UAVs) combined with artificial intelligence (AI) have opened a revolutionized way for mobile crowdsensing (MCS). Conventional AI models, built on aggregation of UAVs’ sensing data (typically contain private and sensitive user information), may arise severe privacy and data misuse concerns. Federated learning, as a promising distributed AI paradigm, has opened up possibilities for UAVs to collaboratively train a shared global model without revealing their local sensing data. However, there still exist potential security and privacy threats for UAV-assisted crowdsensing with federated learning due to vulnerability of central curator, unreliable contribution recording, and low-quality shared local models. In this paper, we propose SFAC, a s ecure f ederated learning framework for U A V-assisted M C S. Specifically, we first introduce a blockchain-based collaborative learning architecture for UAVs to securely exchange local model updates and verify contributions without the central curator. Then, by applying local differential privacy, we design a privacy-preserving algorithm to protect UAVs’ privacy of updated local models with desirable learning accuracy. Furthermore, a two-tier reinforcement learning-based incentive mechanism is exploited to promote UAVs’ high-quality model sharing when explicit knowledge of network parameters are not available in practice. Extensive simulations are conducted, and the results demonstrate that the proposed SFAC can effectively improve utilities for UAVs, promote high-quality model sharing, and ensure privacy protection in federated learning, compared with existing schemes.

Towards Secure and Privacy-Preserving Data Sharing for COVID-19 Medical Records: A Blockchain-Empowered Approach

Abstract: COVID-19 is currently a major global public health challenge. In the battle against the outbreak of COVID-19, how to manage and share the COVID-19 Electric Medical Records (CEMRs) safely and effectively in the world, prevent malicious users from tampering with CEMRs, and protect the privacy of patients are very worthy of attention. In particular, the semi-trusted medical cloud platform has become the primary means of hospital medical data management and information services. Security and privacy issues in the medical cloud platform are more prominent and should be addressed with priority. To address these issues, on the basis of ciphertext policy attribute-based encryption, we propose a blockchain-empowered security and privacy protection scheme with traceable and direct revocation for COVID-19 medical records. The security analysis demonstrates that the proposed scheme is indicated to be safe under the Decision Bilinear Diffie-Hellman (DBDH) assumption and can resist many attacks. The simulation experiment demonstrates that the communication and storage overhead is less than other schemes in the public-private key generation, CEMRs encryption, and decryption stages. Besides, we also verify that the proposed scheme works well in the blockchain in terms of both throughput and delay.

Deep Learning-Embedded Social Internet of Things for Ambiguity-Aware Social Recommendations

Abstract: With the increasing demand of users for personalized social services, social recommendation (SR) has been an important concern in academia. However, current research on SR universally faces two main challenges. On the one hand, SR lacks the considerable ability of robust online data management. On the other hand, SR fails to take the ambiguity of preference feedback into consideration. To bridge these gaps, a deep learning-embedded social Internet of Things (IoT) is proposed for ambiguity-aware SR (SIoT-SR). Specifically, a social IoT architecture is developed for social computing scenarios to guarantee reliable data management. A deep learning-based graph neural network model that can be embedded into the model is proposed as the core algorithm to perform ambiguity-aware SR. This design not only provides proper online data sensing and management but also overcomes the preference ambiguity problem in SR. To evaluate the performance of the proposed SIoT-SR, two real-world datasets are selected to establish experimental scenarios. The method is assessed using three different metrics, selecting five typical methods as benchmarks. The experimental results show that the proposed SIoT-SR performs better than the benchmark methods by at least 10% and has good robustness.

Privacy-Aware Cross-Platform Service Recommendation Based on Enhanced Locality-Sensitive Hashing

Abstract: Recommender systems are a promising way for users to quickly find the valuable information that they are interested in from massive data. Concretely, by capturing the user's personalized preferences, a recommender system can return a list of recommended items that best match the user preferences by using collaborative filtering. However, in the big data environment, the heavily fragmented distribution of the QoS (Quality of Services) data for recommendation decision- making presents a large challenge when integrating the QoS data from different platforms while ensuring that the sensitive user information contained in the QoS data is secure. Furthermore, due to the common tradeoff between data availability and privacy in data-driven applications, protecting the sensitive user information contained in the QoS data will probably decrease the availability of QoS data and finally produce inaccurate recommendation results. Considering these challenges, we enhance the classic Locality-Sensitive Hashing (LSH) technique, after which we propose an approach based on enhanced LSH for accurate and less-sensitive cross-platform recommendation decision-makings. Finally, extensive experiments are designed and tested on the reputable WS-DREAM dataset. The test reports prove the benefits of our work compared to other competitive approaches in the aspects of recommendation accuracy, efficiency and privacy protection performances.

Highly-Accurate Community Detection via Pointwise Mutual Information-Incorporated Symmetric Non-Negative Matrix Factorization

Abstract: Community detection, aiming at determining correct affiliation of each node in a network, is a critical task of complex network analysis. Owing to its high efficiency, Symmetric and Non-negative Matrix Factorization (SNMF) is frequently adopted to handle this task. However, existing SNMF models mostly focus on a network's first-order topological information described by its adjacency matrix without considering the implicit associations among involved nodes. To address this issue, this study proposes a Pointwise mutual information-incorporated and Graph-regularized SNMF (PGS) model. It uses a) Pointwise Mutual Information to quantify implicit associations among nodes, thereby completing the missing but crucial information among critical nodes in a uniform way; b) graph-regularization to achieve precise representation of local topology, and c) SNMF to implement efficient community detection. Empirical studies on eight real-world social networks generated by industrial applications demonstrate that a PGS model achieves significantly higher accuracy gain in community detection than state-of-the-art community detectors.

Many-Objective Deployment Optimization for a Drone-Assisted Camera Network

Abstract: Drone-assisted camera networks can be used in many applications. However, different application requirements lead to different deployment scenarios. In this paper, based on a 3D terrain environment represented by triangular mesh data, a many-objective optimization model for the deployment of multiple onboard cameras is constructed. We propose an improved version of the constrained two-archive evolutionary algorithm. A selection operator based on Gaussian process regression is used for enhancement. Additionally, we quantize the polynomial mutation operator. The improved algorithm is applied to optimize drone-assisted camera deployment, and the experimental results show that the improved algorithm is superior to state-of-the-art algorithms.

Blockchain-Enabled Accountability Mechanism Against Information Leakage in Vertical Industry Services

Abstract: The emergence of 5 G technology contributes to create more open and efficient eco-systems for various vertical industries. Especially, it significantly improves the capabilities of the vertical industries focusing on content-sharing services like mobile telemedicine, etc. However, cyber threats such as information leakage or piracy are more likely to occur in an open 5 G networks. So tracking information leakage in 5 G environments has become a daunting task. The existing tracing and accountability schemes have nonnegligible limitations in practice due to the dependence on a Trusted Third Party (TTP) or being encumbered with the significant overhead. Fortunately, the blockchain helps to mitigate these problems. In this paper, we propose a blockchain-enabled accountability mechanism against information leakage in the content-sharing services of the vertical industry services. For any information converted to vector form, we use the blockchain technology to ensure that service providers and clients can securely and fairly generate and share watermarked content. Besides, the homomorphic encryption is introduced to avoid the disclosure of the watermarking content, which guarantees the subsequent TTP-free arbitration. Finally, we theoretically analyze the security of the scheme and verify its performance.

Improved Deep Convolutional Neural Network based Malicious Node Detection and Energy-Efficient Data Transmission in Wireless Sensor Networks

Abstract: Wireless Sensors Networks (WSN) is the self-configured wireless network which consists of a huge measure of resource-restrained Sensor Nodes (SN). In WSN, the key parameters are effectual energy utilization and security. The adversary could send false information because of the Malicious Nodes' (MNs') presence. Thus, to shun security threats, it is vital to find and isolate those MN. Consequently, this work proffered a solution for detecting MN in WSN utilizing SN's parameters. This work not only regards the security but also rendered energy-efficient data transmission by means of choosing the Cluster Head (CH) centered on the sensor's residual energy. The Improved Deep Convolutional Neural Network (IDCNN) identifies the MN and then isolates them into the malicious list box in the Malicious Nodes Detection (MND) phase. In the energy-efficient DT phase, the EKM algorithm clusters the Trusted Nodes (TN), and, the t-DSBO algorithm selects an individual CH for each cluster centered on those nodes' residual energy. The t-Distribution based Satin Bowerbird Optimization (t-DSBO) selects an alternate CH if the current CH loses its energy. The proposed techniques effectively detect the MN and render energy-efficient DT, which is experimentally proved by comparing it with existing techniques.

An Intelligent Collaboration Trust Interconnections System for Mobile Information Control in Ubiquitous 5G Networks

Abstract: The heterogeneous networks which collaborate among Space, Air, Ground, and Sea (SAGS) networks significantly promote the development of the Internet of Things (IoT). Billions of IoT devices in SAGS networks generate massive data to support various applications. We argue that it is crucial to construct a Collaboration Trust Interconnections System (CTIS) to provide the ubiquitous SAGS network accessibility and security. In this paper, a CTIS framework among the Unmanned Aerial Vehicles (UAV), Mobile Vehicles (MVs), and IoT devices is proposed to evaluate trust and select low-cost and high-trust participants to improve data quality. In this framework, MVs record the interaction information to form the verification chains, while the UAV is dispatched to collect baseline data to verify the data reported by MVs, thereby constructing global trust. Then, the hash values of baseline data are delivered to MVs to act as calibration baseline data, which provides a verification certificate for interactions among MVs and constructs local interaction trust. Finally, a greedy-based winner recruitment strategy is proposed to achieve intelligent information control with maximum credibility and cost. The simulation results show that the CTIS framework reduces the cost by 5.62%, reduces the false ratio and packet dropping rate by at least 17.16% and 31.51% compared with previous schemes.

Intelligent UAVs Trajectory Optimization From Space-Time for Data Collection in Social Networks

Abstract: With rapid development of artificial intelligence (AI) technology, social network (SN) can use AI to extract useful knowledge of users to improve the quality of peoples lives. Although AI has achieved a very big breakthrough, it also faces many challenges for collecting data, such as larger data redundancy and higher energy consumption. To conquer those problems, a matrix completion-based Sampling Points Selection joint Intelligent Unmanned Aerial Vehicle (UAVs) Trajectory Optimization (SPS-IUTO) scheme for data acquisition is proposed. In terms of space, for one column, the probability that a sample point is selected is inversely proportional to the number of sample points selected by all previous rows. In terms of time, the first step is that sampling points with higher degree are selected as dominator sampling points in each row and column. The second step is that sampling points with lower degree are selected as virtual dominator sampling points. The movement trajectory of the UAV is optimized using the proposed algorithm. As is shown in the experimental results, the proposed scheme can achieve significant improvement in terms of energy and redundant data.

VFChain: Enabling Verifiable and Auditable Federated Learning via Blockchain Systems

Abstract: Advanced artificial intelligence techniques, such as the federated learning, has been applied to broad areas, e.g., image classification, speech recognition, smart city, and healthcare. Despite intensive research on the federated learning, existing schemes are vulnerable to attacks and cannot meet the security requirement for real applications. The problem of designing a secure federated learning framework to ensure the correctness of training procedure has not been sufficiently studied and remains open. In this paper, we propose VFChain, a verifiable and auditable federated learning framework based on the blockchain system. First, to provide the verifiability, a committee is selected through the blockchain to collectively aggregate models and record verifiable proofs in the blockchain. Then, to provide the auditability, a novel authenticated data structure is proposed for blockchain to improve the search efficiency of verifiable proofs and support a secure rotation of committee. Finally, to further improve the efficiency, an optimization scheme is proposed to support multiple-model learning tasks. We implement VFChain and conduct extensive experiments by utilizing the popular deep learning model and the public real-world dataset. The evaluation results demonstrate the effectiveness of our proposed VFChain system.

Optimal User-Edge Assignment in Hierarchical Federated Learning based on Statistical Properties and Network Topology Constraints

Abstract: Learning-based applications have demonstrated practical use cases in ubiquitous environments and amplified interest in exploiting the data stored on users' mobile devices. Distributed optimization algorithms aim to leverage such distributed and diverse data to learn a global phenomena by performing training amongst participating devices and repeatedly aggregating their local models' parameters into a global model. Federated Averaging is a promising solution that allows for extending local training before aggregating the parameters, offering better communication efficiency. However, in the cases where the participants' data are strongly skewed (i.e., local distributions are different), the model accuracy can significantly drop. To face this challenge, we leverage the edge computing paradigm to design a hierarchical learning system that performs Federated Gradient Descent on the user-edge layer and Federated Averaging on the edge-cloud layer. In this hierarchical architecture, the users might be assigned to different edges, leading to different edge-level data distributions. We formalize and optimize this user-edge assignment problem to minimize classes' distribution distance between edge nodes, which enhances the Federated Averaging performance. Our experiments on multiple real datasets show that the proposed optimized assignment is tractable and leads to faster convergence of models towards a better accuracy value.

COVID-19 Networking Demand: An Auction-based Mechanism for Automated Selection of Edge Computing Services

Abstract: Network and cloud service providers are facing an unprecedented challenge to meet the demand of end-users during the COVID-19 pandemic. Currently, billions of people around the world are ordered to stay at home and use remote connection technologies to prevent the spread of the disease. The COVID-19 crisis brought a new reality to network service providers that will eventually accelerate the deployment of edge computing resources to attract the massive influx of users' traffic. The user can elect to procure its resource needs from any edge computing provider based on a variety of attributes such as price and quality. The main challenge for the user is how to choose between the price and multiple quality of service deals when such offerings are changing continually. This problem falls under multi-attribute decision-making. This paper investigates and proposes a novel auction mechanism by which network service brokers would be able to automate the selection of edge computing offers to support their end-users. We also propose a multi-attribute decision-making model that allows the broker to maximize its utility when several bids from edge-network providers are present.The evaluation and experimentation show the practicality and robustness of the proposed model.

Dynamic Digital Twin and Federated Learning with Incentives for Air-Ground Networks

Abstract: The air-ground network provides users with seamless connections and real-time services, while its resource constraint triggers a paradigm shift from machine learning to federated learning. Federated learning enables clients to collaboratively train models without sharing data. Meanwhile, digital twins provide environmental awareness and autonomous management, which in combination with federated learning reconciles the conflict between privacy protection and data training in air-ground network. In this paper, we consider dynamic digital twin and federated learning for air-ground networks where drone works as the aggregator and the ground clients collaboratively train the model based on the network dynamics captured by digital twins. We design incentives for federated learning based on Stackelberg game, in which the digital twin of the drone acts as the leader to set preferences for clients, and clients as followers choose the global training rounds after weighing benefits and costs. Furthermore, considering the varying digital twin deviations and network dynamics during the federated learning process, we design a dynamic incentive scheme to adaptively adjust the selection of the optimal clients and their participation level. Numerical results show that the proposed schemes can significantly improve accuracy and energy efficiency.

SEDMDroid: An Enhanced Stacking Ensemble Framework for Android Malware Detection

Abstract: The popularity of the Android platform in smartphones and other Internet-of-Things devices has resulted in the explosive of malware attacks against it. Malware presents a serious threat to the security of devices and the services they provided, e.g. stealing the privacy sensitive data stored in mobile devices. This work raises a stacking ensemble framework SEDMDroid to identify Android malware. Specifically, to ensure individual's diversity, it adopts random feature subspaces and bootstrapping samples techniques to generate subset, and runs Principal Component Analysis (PCA) on each subset. The accuracy is probed by keeping all the principal components and using the whole dataset to train each base learner Multi-Layer Perception (MLP). Then, Support Vector Machine (SVM) is employed as the fusion classifier to learn the implicit supplementary information from the output of the ensemble members and yield the final prediction result. We show experimental results on two separate datasets collected by static analysis way to prove the effectiveness of the SEDMDroid. The first one extracts permission, sensitive API, monitoring system event and so on that are widely used in Android malwares as the features, and SEDMDroid achieves 89.07% accuracy in term of these multi-level static features. The second one, a public big dataset, extracts the sensitive data flow information as the features, and the average accuracy is 94.92%. Promising experiment results reveal that the proposed method is an effective way to identify Android malware.

Event-Triggered Adaptive Fault-Tolerant Pinning Control for Cluster Consensus of Heterogeneous Nonlinear Multi-Agent Systems Under Aperiodic DoS Attacks

Abstract: This paper presents an event-triggered cluster consensus scheme for heterogeneous nonlinear second-order multi-agent systems (MASs) subject to cyber attacks (i.e., aperiodic denial-of-service (DoS) attacks), actuator faults and integral quadratic constraints (IQCs) under directed communication topology containing a directed spanning tree. Based on local communication, an event-triggered adaptive fault-tolerant pinning control scheme is designed to achieve cluster consensus under simultaneous cyber attacks and actuator faults. The proposed control scheme does not require the communication topology to satisfy the in-degree balance between different clusters. Furthermore, the fault-tolerant control part only needs to estimate one parameter for each agent. Instead of requiring continuous information on its neighbors to determine the trigger instants as in the previous literature, an event-triggered mechanism that does not require periodic sampling of neighbors’ information is developed to save network resources, and the Zeno behavior is excluded. Finally, a simulation example confirms the effectiveness and superiority of the proposed control scheme.

AESMOTE: Adversarial Reinforcement Learning With SMOTE for Anomaly Detection

Abstract: Intrusion Detection Systems (IDSs) play a vital role in securing today's Data-Centric Networks In a dynamic environment such as the Internet of Things (IoT), which is vulnerable to various types of attacks, fast and robust solutions are in demand to handle fast-changing threats and thus the ever-increasing difficulty of detection In this paper, we present a novel framework for the detection of anomalies, which, in particular, supports intrusion detection The anomaly-detection framework we propose combines reinforcement learning with class-imbalance techniques Our goal is not only to exploit the auto-learning ability of the reinforcement-learning loop but also to address the dataset imbalance problem, which is pervasive in existing learning-based solutions We introduce an adapted SMOTE to address the class-imbalance problem while remodelling the behaviors of the environment agent for better performance Experiments are conducted on NSL-KDD datasets Comparative evaluations and their results are presented and analyzed Using techniques such as SMOTE, ROS, NearMiss1 and NearMiss2, performance measures obtained from our simulations have led us to recognize specific performance trends In particular, the proposed model AESMOTE outperforms AE-RL in several cases Experiment results show an Accuracy greater than 082 and a F1 greater than 0824

FedSteg: A Federated Transfer Learning Framework for Secure Image Steganalysis

Abstract: The protection of user private data has long been the focus of AI security. We know that training machine learning models rely on large amounts of user data. However, user data often exists in the form of isolated islands that can not be integrated under many secure and legal constraints. The large-scale application of image steganalysis algorithms in real life is still not satisfactory due to the following challenges. First, it is difficult to aggregate all of the scattered steganographic images to train a robust classifier. Second, even if the images are encrypted, participants do not want irrelevant people to peek into the hidden information, resulting in the disclosure of private data. Finally, it is often impossible for different participants to train their tailored models. In this paper, we introduce a novel framework, referred to as FedSteg, to train a secure, personalized distributed model through federated transfer learning to fulfill secure image steganalysis. Extensive experiments on detecting several state-of-the-art steganographic methods i.e., WOW, S-UNIWARD, and HILL, validate that FedSteg achieves certain improvements compared to traditional non-federated steganalysis approaches. In addition, FedSteg is highly extensible and can be easily employed to various large-scale secure steganographic recognition tasks.

Periodic-Aware Intelligent Prediction Model for Information Diffusion in Social Networks

Abstract: Due to the rapid development of information and communication technologies with several emerging computing paradigms, such as ubiquitous computing, social computing, and mobile computing, modeling of information diffusion becomes an increasingly significant issue in the big data era. In this study, we focus on a periodic-aware intelligent prediction method based on a comprehensive modeling of user and contagion features, which can be applied to support information diffusion across social networks in accordance with users’ adoption behaviors. In particular, the Dynamically Socialized User Networking (DSUN) model and sentiment-Latent Dirichlet Allocation (LDA) topic model, which consider a series of social factors, including user interests and social roles, semantic topics and sentiment polarities, are constructed and integrated together to facilitate the information diffusion process. A periodic-aware preception mechanism usingreinforcement learning with a newly designed reward rule based on topic distribution is then designed to detect and classify different periods into the so-called routine period and emergency period. Finally, a deep learning scheme based on multi-factor analysis is developed for adoption behavior prediction within the identified different periods. Experiments using the real-world data demonstrate the effectiveness and usefulness of our proposed model and method in heterogenous social network environments.

Fault-Resilience for Bandwidth Management in Industrial Software-Defined Networks

Abstract: In this paper, we address a key challenge of managing required bandwidth for traffic flows in Industrial cyber-physical systems (ICPS). To manage the required bandwidth and to improve fault-resilience in such Industrial networks, software-defined networks (SDN) are used. We propose a contract-based framework with the use of SDN where the components are bound to bandwidth-contracts and a resilience manager. The bandwidth-contracts state the bandwidth requirements of the traffic flows. Based on the newly calculated routes, an observer detects whether the contract still satisfies the bandwidth requirements of the traffic flows or the contract gets violated (termed as fault). To provide resilience to such faults in the network, a resilience manager integrated with control logic, decides and executes a suitable response strategy (depending upon the severity of the fault). The proposed framework is evaluated using Ryu SDN controller on hardware testbed. Different tests on the hardware testbed depict that the proposed framework provides enhanced network resilience as compared to the base-line mechanisms. Besides, our extensive experimental emulations are carried out on the Mininet SDN tool for testing the scalability of the proposed framework.

Security-Aware Virtual Network Embedding Algorithm Based on Reinforcement Learning

Abstract: Virtual network embedding (VNE) algorithm is always the key problem in network virtualization (NV) technology. At present, the research in this field still has the following problems. The traditional way to solve VNE problem is to use heuristic algorithm. However, this method relies on manual embedding rules, which does not accord with the actual situation of VNE. In addition, as the use of intelligent learning algorithm to solve the problem of VNE has become a trend, this method is gradually outdated. At the same time, there are some security problems in VNE. However, there is no intelligent algorithm to solve the security problem of VNE. For this reason, this paper proposes a security-aware VNE algorithm based on reinforcement learning (RL). In the training phase, we use a policy network as a learning agent and take the extracted attributes of the substrate nodes to form a feature matrix as input. The learning agent is trained in this environment to get the mapping probability of each substrate node. In the test phase, we map nodes according to the mapping probability and use the breadth-first strategy (BFS) to map links. For the security problem, we add security requirements level constraint for each virtual node and security level constraint for each substrate node. Virtual nodes can only be embedded on substrate nodes that are not lower than the level of security requirements. Experimental results show that the proposed algorithm is superior to other typical algorithms in terms of long-term average return, long-term revenue consumption ratio and virtual network request (VNR) acceptance rate.

A Privacy-Preserving Federated Learning for Multiparty Data Sharing in Social IoTs

Abstract: As 5G and mobile computing are growing rapidly, deep learning services in the Social Computing and Social Internet of Things (IoT) have enriched our lives over the past few years. Mobile devices and IoT devices with computing capabilities can join social computing anytime and anywhere. Federated learning allows for the full use of decentralized training devices without the need for raw data, providing convenience in breaking data silos further and delivering more precise services. However, the various attacks illustrate that the current training process of federal learning is still threatened by disclosures at both the data and content levels. In this paper, we propose a new hybrid privacy-preserving method for federal learning to meet the challenges above. First, we employ an advanced function encryption algorithm that not only protects the characteristics of the data uploaded by each client, but also protects the weight of each participant in the weighted summation procedure. By designing local Bayesian differential privacy, the noise mechanism can effectively improve the adaptability of different distributed data sets. In addition, we also use Sparse Differential Gradient to improve the transmission and storage efficiency in federal learning training. Experiments show that when we use the sparse differential gradient to improve the transmission efficiency, the accuracy of the model is only dropped by 3% at most.

Secure Social Internet of Things Based on Post-Quantum Blockchain

Abstract: With the advancement of the application of Internet of Things (IoTs), the IoT technology is combining with the social network, forming a new network with private object information as the media and social entertainment as the purpose. Social Internet of things (SIoTs) is a new application of IoT technology in social network. The current SIoT systems are centralized and the user's security and privacy is not properly protected. In order to address the challenges in SIoTs, we propose a privacy protection system for the users. First, we propose a post-quantum ring signature. Second, we propose a blockchain system based on the ring signature. Compared with the traditional SIoTs, our system is based on post-quantum techniques, which is secure against both traditional computers and quantum computers. The results of the blockchain system show that it is very suitable for SIoTs.

Ethna: Analyzing the Underlying Peer-to-Peer Network of Ethereum Blockchain

Abstract: The peer-to-peer (P2P) network of blockchain used to transport its transactions and blocks has a high impact on the efficiency and security of the system. The P2P network topologies of popular blockchains such as Bitcoin and Ethereum, therefore, deserve our highest attention. The current Ethereum blockchain explorers (e.g., Etherscan) focus on the tracking of block and transaction records but omit the characterization of the underlying P2P network. This work presents the Ethereum Network Analyzer (Ethna), a tool that probes and analyzes the P2P network of the Ethereum blockchain. Unlike Bitcoin that adopts an unstructured P2P network, Ethereum relies on the Kademlia DHT to manage its P2P network. Therefore, the existing analytical methods for Bitcoin-like P2P networks are not applicable to Ethereum. Ethna implements a novel method that accurately measures the degrees of Ethereum nodes. Furthermore, it incorporates an algorithm that derives the latency metrics of message propagation in the Ethereum P2P network. We ran Ethna on the Ethereum Mainnet and conducted extensive experiments to analyze the topological features of its P2P network. Our analysis shows that the Ethereum P2P network possesses a certain effect of small-world networks, and the degrees of nodes follow a power-law distribution that characterizes scale-free networks.