Search

With the increase of private cars, traditional traffic signal control methods cannot alleviate the traffic congestion problem. Reinforcement learning (RL) is increasingly used in adaptive traffic light control. As urban traffic becomes more complex, reinforcement learning algorithms solely based on value or policy are not suitable for such scenarios. Moreover, the centralized method does not show a good effect on the multi-intersection, in particular, when the traffic flow is in the high-dimensional continuous state space. In this article, we propose a decentralized framework based on the advantage actor-critic (A2C) algorithm by assigning global control to each local RL agent or intersection. A2C algorithm involved in this article is a product of combining policy function and value function, which has good convergence ability and can be applied to continuous state space. The decentralized methods may put a new challenge: from the perspective of each local agent, the environment becomes partially observable. We overcome this problem by putting forward a region-aware cooperative strategy (RACS) based on graph attention network (GAT), which can incorporate the spatial information of the surrounding agents. We carry out experiments on synthetic traffic grid and real-world traffic network of Monaco city to compare with the existing A2C and Q-learning algorithms. Experimental results confirm that our RACS method has a shorter queue length and less waiting time than the two existing algorithms, and can reduce the total vehicle travel time.

In cloud storage, how to search sensitive data efficiently and securely is a challenging problem. The searchable encryption technique provides a secure storage method without loss of data confidentiality and utilization. As an important branch of searchable encryption, public-key encryption with keyword search (PEKS) is widely studied by scholars. However, most of the traditional PEKS schemes are vulnerable to the inside keyword guessing attack (IKGA) or some other weaknesses. Resisting the inside keyword guessing attack is likely to become a must-have property of all new PEKS schemes. For a long time, mitigating IKGA has been inefficient and difficult, and thus most existing PEKS schemes fail in achieving their security goals. To improve the security and efficiency of PEKS, we define the notion of Dual-server Public-key Authenticated Encryption with Keyword Search (DPAEKS), which protects against IKGA with high computation efficiency, and supports the authentication property. Then, we provide a construction of DPAEKS without bilinear pairings, which is secure against IKGA by leveraging two servers that do not cooperate. Experimental results obtained using a real-world dataset show that our scheme is highly efficient and provides strong security, making it suitable for deployment in practical applications.

As more data from Industrial Internet of Things (IIoT) devices are been outsourced to the cloud, the need to ensure/achieve data privacy will be increasingly pressing. Searchable public-key encryption is a promising tool to achieve data privacy without sacrificing data usability. However, most existing searchable public-key encryption schemes are either inefficient (e.g., expensive in terms of encryption and searching keywords) or lack the required (security) features such as forward privacy. To address these limitations, we propose a lightweight searchable public-key encryption with forward privacy. Specifically, the scheme allows us to achieve forward privacy in a public-key cryptography (i.e., asymmetric) setting, and has the same search performance as a number of practical searchable symmetric encryption schemes. The formal security analysis shows that the proposed scheme is chosen-keyword attack resilient and achieves forward privacy. Finally, the experimental results on a real-world dataset demonstrate that the proposed scheme is highly efficient and scalable in IIoT applications.

The reliability and validity of traffic data plays an important role in intelligent transportation systems. Most of the data detection schemes target the network level, and rarely discuss the impact of vehicle data detection at intersections on the intelligent control of traffic lights. Moreover, most data detection is processed in a centralized cloud center, which is not suitable for complex and changeable intersections. In this regard, we propose an edge computing based data detection scheme for traffic light intersections. In our scheme, traffic lights act as edge nodes to detect vehicles data. We first consider a single intersection scenario. We collect vehicle data through V2E communication through base station, and use the quotient filter to detect and verify the validity of the data. We further consider the multiple intersections scenario. We merge the vehicle data of the two adjacent intersections, and then detect the validity of the data by the quotient filter. In addition, the scheme uses mmh3 hash functions in the QF filter to reduce the computing resource occupation of edge nodes and the bit error rate. The experimental results show that the data detection solution is effective in detecting data quickly even there is a large number of vehicles and complex vehicle data. Our proposed scheme can also verify the reliability and effectiveness of vehicles with a smaller delay.

Internet of Things (IoT)-enabled smart grids can achieve more reliable and high-frequency data collection and transmission compared with existing grids. However, this frequent data processing may consume a lot of bandwidth, and even put the user’s privacy at risk. Although many privacy-preserving data aggregation schemes have been proposed to solve the problem, they still suffer from some security weaknesses or performance deficiency, such as lack of satisfactory data confidentiality and resistance to malicious data mining attack. To address these issues, we propose a novel privacy-preserving data aggregation scheme (called PDAM) for IoT-enabled smart grids, which can support efficient data source authentication and integrity checking, secure dynamic user join and exit. Unlike existing schemes, the PDAM is resilient to the malicious data mining attack launched by internal or external attackers and can achieve perfect data confidentiality against not only a malicious aggregator but also a curious control center for an authorized user. The detailed security and performance analysis show that our proposed PDAM can satisfy several well-known security properties and desirable efficiency for a smart grid system. Moreover, the comparative studies and experiments demonstrate that the PDAM is superior to other recently proposed works in terms of both security and performance.

Vehicular ad hoc networks ( VANETs ) and the services they support are an essential part of intelligent transportation. Through physical technologies, applications, protocols, and standards, they help to ensure traffic moves efficiently and vehicles operate safely. This article surveys the current state of play in VANETs development. The summarized and classified include the key technologies critical to the field, the resource-management and safety applications needed for smooth operations, the communications and data transmission protocols that support networking, and the theoretical and environmental constructs underpinning research and development, such as graph neural networks and the Internet of Things. Additionally, we identify and discuss several challenges facing VANETs, including poor safety, poor reliability, non-uniform standards, and low intelligence levels. Finally, we touch on hot technologies and techniques, such as reinforcement learning and 5G communications, to provide an outlook for the future of intelligent transportation systems.

Worker recruitment is an important problem in mobile crowdsourcing (MCS), which aims to find sufficient and suitable participants to perform tasks. However, existing worker recruitment approaches mainly focus on how to select the most suitable workers for tasks from a large worker pool, while the recruitment problem under insufficient workers (e.g., a new MCS system) has not been well addressed. In this paper, we focus on the insufficient participation problem of MCS systems with limited number of workers, and propose to leverage social network to recruit workers for task completion as well as expanding the worker pool. To this end, we propose a dynamic incentive mechanism, called SocialRecruiter, to encourage workers on the MCS platform to propagate tasks through social networks, so that inviting friends to join in the MCS platform to further propagate and complete tasks. Motivated by the SIR epidemic model, we propose a novel task-specific epidemic model to characterize the status change of users for task propagation and completion through social networks. In order to encourage task completion and propagation, the propagating reward and completing reward are provided according to workers’ actions. In particular, in order to maximize the task completion within the financial budget, the propagating and completing rewards are dynamically updated at each cycle according to real-time worker recruitment progress. The extensive experimental results on two real-world datasets demonstrate that SocialRecruiter outperforms the state-of-the-art approaches in terms of worker recruitment and task completion.

As the use of machine learning in the Internet-of-Medical Things (IoMT) settings increases, so do the data privacy concerns. Therefore, in this article, we propose an efficient privacy-preserving outsourced support vector machine scheme (EPoSVM), designed for IoMT deployment. To securely train the support vector machine (SVM), we design eight secure computation protocols to allow the cloud server to efficiently execute basic integer and floating-point computations. The proposed scheme protects training data privacy and guarantees the security of the trained SVM model. The security analysis proves that our proposed protocols and EPoSVM satisfy both security and privacy protection requirements. Findings from the performance evaluation using two real-world disease data sets also demonstrate the efficiency and effectiveness of EPoSVM in achieving the same classification accuracy as a general SVM.

It is important to transmit data reliably, and efficiently in vehicular networks. Existing works usually study routing strategies, and cooperative scheduling to improve the efficiency of transmission. However, the data transmission remains inefficient because of the lack of full use of communication resources. The transmission is unreliable because information cannot be completely transmitted to the destination vehicles. Moreover, the increasing number of connected vehicles, and the limitation of available communication resources make task scheduling challenging in vehicular networks. In this work, we propose C luster-enabled C ooperative S cheduling based on R einforcement L earning (CCSRL) to improve the communication efficiency, and reliability of vehicular networks, with the goal of maximizing the information capacity. In particular, we leverage the stability to select a cluster head vehicle to enhance data transmission efficiency, and a reinforcement learning-based auxiliary transmission is further designed to guarantee the reliable communication among vehicles. The experimental results demonstrate that the performance of the proposed scheduling algorithm, especially the performance of the packet delivery ratio, and node packet loss ratio, is better than that of the state-of-the-art algorithm.

Summary This paper studies the problem of observer‐based finite time adaptive fault tolerant control for nonaffine nonlinear systems with actuator faults and disturbances. Based on mean value theor...

As the integration of the Internet of Vehicles and social networks, vehicular social networks (VSN) not only improves the efficiency and reliability of vehicular communication environment, but also provide more comprehensive social services for users. However, with the emergence of advanced communication and computing technologies, more and more data can be fast and conveniently collected from heterogeneous devices, and VSN has to meet new security challenges such as data security and privacy protection. Searchable encryption (SE) as a promising cryptographic primitive is devoted to data confidentiality without sacrificing data searchability. However, most existing schemes are vulnerable to the adaptive leakage-exploiting attacks or can not meet the efficiency requirements of practical applications, especially the searchable public-key encryption schemes (SPE). To achieve secure and efficient keyword search in VSN, we design a new blockchain-based searchable public-key encryption scheme with forward and backward privacy (BSPEFB). BSPEFB is a decentralized searchable public-key encryption scheme since the central search cloud server is replaced by the smart contract. Meanwhile, BSPEFB supports forward and backward privacy to achieve privacy protection. Finally, we implement a prototype of our basic construction and demonstrate the practicability of the proposed scheme in applications.

The rapid development of machine learning has spurred wide applications to various industries, where prediction models are built to forecast sales to help enterprises and governments make better plans. Alibaba Cloud and the Yancheng Municipal Government held a competition in 2018, calling for global efforts to build machine learning models that can accurately forecast vehicle sales based on large-scale datasets. This paper presents the design, implementation and evaluation of ForeXGBoost, and our proposed model that won the first place in the competition. ForeXGBoost takes full advantage of carefully-designed data filling algorithms for missing values to improve data quality. By using the sliding window to extract historical sales and production data features, ForeXGBoost can improve prediction accuracy. An extensive study is conducted to evaluate the influence of different attributes on vehicle sales via information gain and data correlation, based on which we select the most indicative features from the feature set for prediction. Furthermore, we leverage the XGBoost prediction algorithm to achieve a high prediction accuracy with short running time for vehicle sales prediction. Extensive experiments confirm that ForeXGBoost can achieve a high prediction accuracy with a low overhead.

Achieving low latency and providing real-time services are two of several key challenges in conventional cloud-based smart grid systems, and hence, there has been an increasing trend of moving to edge computing. While there have been a number of cryptographic protocols designed to facilitate secure communications in smart grid systems, existing protocols generally do not support conditional anonymity and flexible key management. Thus, in this article, we introduce a blockchain-based mutual authentication and key agreement protocol for edge-computing-based smart grid systems. Specifically, leveraging blockchain, the protocol can support efficient conditional anonymity and key management, without the need for other complex cryptographic primitives. The security analysis shows that the protocol achieves reasonable security assurance, and the comparative summary for security and efficiency also suggests the potential of the proposed protocol in a smart grid deployment.

In this study, an adaptive neural backstepping control scheme is proposed for a class of nonstrict-feedback time-delay systems with input saturation, full-state constraints and unknown disturbances. A structural property of radial basis function neural network is presented to deal with the design from the nonstrict-feedback formation. This method does not require the parameter separation technique and its assumption. With the help of the Lyapunov-Krasovskii functionals and Young’s inequalities, the effects of time delays are compensated, and the unknown disturbances are eliminated in the design process. The barrier Lyapunov function (BLF) is applied to arrest the violation of the full-state constraints. To overcome the problem of input saturation nonlinearity, the smooth nonaffme function of the control input signal is adopted to approach the input saturation function. Moreover, an adaptive backstepping neural control strategy is proposed. The proposed adaptive neural controller ensures that all the closed-loop signals are semi-globally uniformly ultimately bounded (SGUUB). Furthermore, the tracking error can converge to a small neighborhood of the origin. The simulation result shows the effectiveness of this method.

Data sharing through the cloud is flourishing with the development of cloud computing technology. The new wave of technology will also give rise to new security challenges, particularly the data confidentiality in cloud-based sharing applications. Searchable encryption is considered as one of the most promising solutions for balancing data confidentiality and usability. However, most existing searchable encryption schemes cannot simultaneously satisfy requirements for both high search efficiency and strong security due to lack of some must-have properties, such as parallel search and forward security. To address this problem, we propose a variant searchable encryption with parallelism and forward privacy, namely the parallel and forward private searchable public-key encryption (PFP-SPE). PFP-SPE scheme achieves both the parallelism and forward privacy at the expense of slightly higher storage costs. PFP-SPE has similar search efficiency with that of some searchable symmetric encryption schemes but no key distribution problem. The security analysis and the performance evaluation on a real-world dataset demonstrate that the proposed scheme is suitable for practical application.

Voice authentication is becoming increasingly popular, which offers potential benefits over knowledge and possession based authentication methods. Meanwhile, the unique features of lip movements during speaking have been proved to be useful for authentication. However, the unimodal biometric authentication systems based on either voice or lip movements have certain limitations. Voice authentication systems are prone to spoofing attacks and suffer from serious performance degradation in noisy environments. Lip movements authentication systems are unstable and are sensitive to the user’s physical and psychological conditions. In this paper, we propose and implement LVID, a multimodal biometrics authentication system on smartphones, which resolves the defects of the original systems by combining the advantages of lip movements and voice. LVID simultaneously captures these two biometrics with the built-in audio devices on smartphones and fuses them at the data level. The reliable and effective features are then extracted from the fused data for authentication. LVID is practical as it requires neither cumbersome operations nor additional hardwares but only a speaker and a microphone that are commonly available on smartphones. Our experimental results with 104 participants show that LVID can achieve 95% accuracy for user authentication, and 93.47% of the attacks can be detected. It is also verified that LVID works well with different smartphones and is robust to different smartphone positions.

This letter presents an improved MADM network selection algorithm based on comprehensive utility function for HVN. Compared with several other MADM based algorithms, the proposed one has fewer handovers, shorter handover delays, which alleviates the network load effectively. These make it is more suitable for HVN.

Adaptive traffic signal control plays a significant role in the construction of smart cities. This task is challenging because of many essential factors, such as cooperation among neighboring intersections and dynamic traffic scenarios. First, to facilitate cooperation of traffic signals, existing work adopts graph neural networks to incorporate the temporal and spatial influences of the surrounding intersections into the target intersection, where spatial-temporal information is used separately. However, one drawback of these methods is that the spatial-temporal correlations are not adequately exploited to obtain a better control scheme. Second, in a dynamic traffic environment, the historical state of the intersection is also critical for predicting future signal switching. Previous work mainly solves this problem using the current intersection's state, neglecting the fact that traffic flow is continuously changing both spatially and temporally and does not handle the historical state. In this paper, we propose a novel neural network framework named DynSTGAT, which integrates dynamic historical state into a new spatial-temporal graph attention network to address the above two problems. More specifically, our DynSTGAT model employs a novel multi-head graph attention mechanism, which aims to adequately exploit the joint relations of spatial-temporal information. Then, to efficiently utilize the historical state information of the intersection, we design a sequence model with the temporal convolutional network (TCN) to capture the historical information and further merge it with the spatial information to improve its performance. Extensive experiments conducted in the multi-intersection scenario on synthetic data and real-world data confirm that our method can achieve superior performance in travel time and throughput against the state-of-the-art methods., I need to revise it

Traffic light control is an extremely challenging problem in transportation. Recently, an increasing number of studies have employed reinforcement learning approaches to deal with traffic light control problems. However, these studies often observe the target intersection independently and ignore the dynamic effects from the surrounding intersections. Moreover, the dependence of historical information on current traffic conditions is also not fully exploited in multi-intersection traffic light control. In this work, we propose a spatial-temporal graph attention network based multi-agent deep Q-learning model. Our model can capture not only spatial features but also temporal features. Specifically, we first utilize the Graph Attention Network (GAT) to obtain the spatial relationship between the central intersection and surrounding intersections. Then Long Short-Term Memory (LSTM) network and the self-attention mechanism are used to get the time dimension information. Finally, we adopt a deep Q-learning network (DQN) to predict the action-value of each feasible action and choose the signal phase according to the size of the action-value. Experimental results on synthetic and realworld datasets confirm that our method can lead to both the least travel time and the maximum throughput, compared with some existing baselines.

In recent years, Convolutional Neural Networks (CNN s) have been widely applied in various applications due to its powerful learning capability. However, its lack of explainability hinders its further usage in tasks requiring high reliability. Therefore, interpretability technique is the key to the application and deployment of CNN models. As a typical interpretability technique for CNN, Class Activation Map (CAM) utilizing the gradient based weights and activation map is widely applied to traditional CNN models for offering visual interpretability. However, the activation map adopted by CAM cannot loyally quantify the relevance between input samples and activation values. Hence, in this paper, we propose a new interpretability approach called Salience-CAM employing salience scores to accurately measure the relevance between input samples and activation values. To evaluate the effectiveness of Salience-CAM, comprehensive experiments are conducted on 6 selected time series datasets. By leveraging an evaluation algorithm proposed in this paper, the experimental results show that our proposed Salience-CAM outperforms the baseline by discovering more discriminative features.

Due to the dynamic characteristics of news and user preferences, personalized recommendation is a challenging problem. Traditional recommendation methods simply focus on current reward, which just recommend items to maximize the number of current clicks. And this may reduce users' interest in similar items. Although the news recommendation framework based on deep reinforcement learning preciously proposed (i.e, DRL, based on deep Q-learning) has the advantages of focusing on future total rewards and dynamic interactive recommendation, it has two issues. First, its exploration method is slow to converge, which may bring new users a bad experience. Second, it is hard to train on off-line data set because the reward is difficult to be determined. In order to address the aforementioned issues, we propose a framework named DEN-DQL for news recommendation based on deep Q-learning with double exploration networks. Also, we develop a new method to calculate rewards and use an off-line data set to simulate the online news clicking environment to train DEN-DQL. Then, the well trained DEN-DQL is tested in the online environment of the same data set, which demonstrates at least 10% improvement of the proposed DEN-DQL., This paper is accepted by International Joint Conference on Neural Networks (IJCNN) 2021

With the networks becoming complex, traditional congestion control protocols face increasing challenges in providing high-quality services for users. Traditional TCP and its variants fail to achieve high performance due to drawbacks in architectural design: predefined actions to specific network feedback. In this paper, we develop a learning-based TCP congestion control scheme RLCC, featuring a deep Q-network framework, in which senders learn the optimal control policies from observations instead of predefined rules. To apply DQN algorithms to congestion control problems, we first prove theoretically that congestion control problems are of Markov property. Therefore, the model-free reinforcement learning algorithm DQN can be used to solve congestion control. This is because the application of DQN to the network congestion control problem is convergent, and there exists an optimal strategy to obtain the best action for congestion control. We improved the network's performance by carefully designing the reward function and choosing the appropriate form and parameters through extensive experimentation. Extensive experiments on real-world environments of Pantheon via AWS confirm that RLCC can achieve utilization improvements over the traditional TCP congestion control schemes with higher throughput and lower transmission latency, and outperform the recently proposed learning-based congestion control protocol.

Time series classification (TSC) is widely used in various real-world applications such as human activity recognition, smart city governance, etc. Unfortunately, due to different reasons, only part of time series could be collected which may obviously degrade the performance of time series classifiers. To alleviate this problem, time series augmentation aims to generate synthetic time series by learning useful features from collected time series. As the popular generative model, generative adversarial networks (GAN) is regarded as a promising model for time series augmentation. However, applying GAN to the time series data suffers from a challenge in which the generated instances hold low quality but the model has gotten saturation. In this paper, for time series augmentation, we proposed TSA-GAN which is a robust GAN model with a self-adaptive recovering strategy to solve this problem. On 85 datasets of the UCR 2015 archive, our proposed TSA-GAN helps time series classifiers achieve performance improvements ranging from 8.3% to 12.5%, which is far better than the baseline.

Probing techniques are widely used to identify faulty nodes in networks. Existing probe-based solutions for SDN fault localizationcan focus on two ways: per-rule and per-path. Both promote some certain switches to reporters by installing on them report rules. To avoid hindering other test packets, such report rules must vary between tests or be deleted before a next test, thus incurring excessive consumption on either TCAM resources of switches or bandwidth reserved for control messages. In this paper we present Voyager, a hybrid fault localization solution for SDN that fully combines the advantages of per-rule and per-path tests. Voyager significantly reduces the number of report rules and allows them to reside and function in switches persistently. With only one well-designed report rule for each switch installed, Voyager pinpoints faulty switches easily and tightly by sending test packets straight. Tests in Voyager are parallelizable and report rules are non-invasive. The performance evaluation on realistic datasets shows that Voyager is 24.0% to 92.3% faster than existing solutions.

The advent of new network architectures has resulted in the rise of network applications with different network performance requirements: live video streaming applications require low latency. In contrast, file transfer applications require high throughput. Existing congestion control protocols may fail to simultaneously meet the performance requirements of these different types of applications since their designed objective function is fixed and difficult to readjust according to the needs of the application. In this paper, we develop MOCC (Multi-Objective Congestion Control), a novel multi-objective congestion control protocol that can meet the performance requirements of different applications without the need to redesign the objective function. MOCC leverages multi-objective reinforcement learning with preferences in order to adapt to different types of applications. By addressing challenges such as slow convergence speed and the difficulty of designing the end of the episode, MOCC can quickly converge to the equilibrium point and adapt multi-objective reinforcement learning to congestion control. Through an extensive array of experiments, we discover that MOCC outperforms the most recent state-of-the-art congestion control protocols and can achieve a trade-off between throughput, latency, and packet loss, meeting the performance requirements of different types of applications by setting preferences.

Recent advances in wireless communication, sensing, computation and control technologies have paved the way for the development of a new era of Internet of Vehicles (IoV). Demanded by the requirements of information-centric and data-driven intelligent transportation systems (ITS), it is of great significance to explore new paradigms of IoV in supporting large-scale, real-time, and reliable information services. In this article, we propose a hierarchical system architecture, which aims at synthesizing the paradigms of software defined networking and fog computing in IoV and best exploiting their synergistic effects on information services. Specifically, a four-layer architecture is designed, comprising the application layer, the control layer, the virtualization layer, and the data layer, with objectives of enabling logically centralized control via the separation of the control plane and the data plane; facilitating adaptive resource allocation and QoS oriented services based on network functions virtualization and network slicing, and enhancing system scalability, responsiveness, and reliability by exploiting the networking, computation, communication, and storage capacities of fog-based services. On this basis, we further analyze newly arising challenges and discuss future research directions by presenting a cross-layer protocol stack. Finally, for the proof of concept, we implement the system prototype and give two case studies in real-world IoV environments. The results of field tests not only demonstrate the great potential of the new architecture, but also give insight into the development of future ITS.

Adaptive traffic light scheduling based on realtime traffic information processing has proven effective for urban traffic congestion management. However, fine-grained information regarding individual vehicles is difficult to acquire through traditional data collection techniques and its accuracy cannot be guaranteed because of congestion and harsh environments. In this study, we first build a pipeline model based on vehicle-to-infrastructure communication, which is a salient technique in vehicular adhoc networks. This model enables the acquisition of fine-grained and accurate traffic information in real time via message exchange between vehicles and roadside units. We then propose an intelligent traffic light scheduling method (ITLM) based on a “demand assignment” principle by considering the types and turning intentions of vehicles. In the context of this principle, a signal phase with more vehicles will be assigned a longer green time. Furthermore, a green-way traffic light scheduling method (GTLM) is investigated for special vehicles (e.g., ambulances and fire engines) in emergency scenarios. Signal states will be adjusted or maintained by the traffic light control system to keep special vehicles moving along smoothly. Comparative experiments demonstrate that the ITLM reduces average wait time by 34%–78% and average stop frequency by 12%–34% in the context of traffic management. The GTLM reduces travel time by 22%–44% and 30%–55% under two types of traffic conditions and achieves optimal performance in congested scenarios.

Online social networking applications have become more and more popular in the advance of the technological age. Much of our personal information has been disclosed in social networking activities and privacy-preserving still remains a research challenge in social network. Public key encryption scheme with equality test(PKEET), which is an extension of public key encryption with keyword search (PEKS), seems to be a solution. PKEET enables the tester to check whether two given ciphertexts are derived from the same plaintext. Recently, Zhu et al. proposed a pairing-free public key encryption scheme with equality test based on the traditional public key cryptosystem. However, it suffers from certificates management issue. In this paper, we propose a pairing-free identity-based encryption scheme with authorized equality test(PF-IBEAET). The PF-IBEAET scheme also provides fine-grained authorizations. We prove that the scheme is one way secure against chosen identity and chosen ciphertext attack (OW-ID-CCA) and indistinguishable against chosen-identity and chosen-ciphertext attack (IND-ID-CCA) in the random oracle model (ROM). Performance analysis shows that the scheme achieves a better performance than similar schemes.

The continuous publication of aggregate statistics over crowd-sourced data to the public has enabled many data mining applications (e.g., real-time traffic analysis). Existing systems usually rely on a trusted server to aggregate the spatio-temporal crowd-sourced data and then apply differential privacy mechanism to perturb the aggregate statistics before publishing to provide strong privacy guarantee. However, the privacy of users will be exposed once the server is hacked or cannot be trusted. In this paper, we study the problem of real-time crowd-sourced statistical data publishing with strong privacy protection under an untrusted server. We propose a novel distributed agent-based privacy-preserving framework, called DADP, that introduces a new level of multiple agents between the users and the untrusted server. Instead of directly uploading the check-in information to the untrusted server, a user can randomly select one agent and upload the check-in information to it with the anonymous connection technology. Each agent aggregates the received crowd-sourced data and perturbs the aggregated statistics locally with Laplace mechanism. The perturbed statistics from all the agents are further combined together to form the entire perturbed statistics for publication. In particular, we propose a distributed budget allocation mechanism and an agent-based dynamic grouping mechanism to realize global $w$w-event $\epsilon$e-differential privacy in a distributed way. We prove that DADP can provide $w$w-event $\epsilon$e-differential privacy for real-time crowd-sourced statistical data publishing under the untrusted server. Extensive experiments on real-world datasets demonstrate the effectiveness of DADP.

As mobile devices ownership becomes more prevalent (e.g., a user owns multiple mobile devices), the capability to offer secure and user friendly authentication becomes increasingly important. A large number of identity-based user authentication mechanisms for the wireless mobile environment have been proposed. However, they are not generally designed for situations where a user’s private key and some other sensitive data can be exposed if his/her mobile device is remotely or physically controlled by an attacker. Threshold secret sharing is one of the solutions to this problem, but it is limited in the requirement that there should exist an honest third-party to hold the complete key after the secret reconstruction process. Therefore, in this paper, we consider the special case that only two devices (i.e., no honest party) at the user’s side jointly perform user authentication with a server, and neither device can successfully complete the authentication process alone. Moreover, the key reconstruction is not needed during authentication so that neither device can hold a complete key. We then analyze the security of the proposed protocol and show that it satisfies all known security requirements in practical applications, particularly the key exposure attack resistance. The performance analysis of the proposed protocol is also presented to demonstrate its practicality.

Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for users and items in an independent and static manner. That is, a single static feature vector is derived to encode user preference without considering the particular characteristics of each candidate item. We argue that this static encoding scheme is incapable of fully capturing users’ preferences, because users usually exhibit different preferences when interacting with different items. In this article, we propose a novel c ontext- a ware user-item r epresentation l earning model for rating prediction, named CARL. CARL derives a joint representation for a given user-item pair based on their individual latent features and latent feature interactions. Then, CARL adopts Factorization Machines to further model higher order feature interactions on the basis of the user-item pair for rating prediction. Specifically, two separate learning components are devised in CARL to exploit review data and interaction data, respectively: review-based feature learning and interaction-based feature learning . In the review-based learning component, with convolution operations and attention mechanism, the pair-based relevant features for the given user-item pair are extracted by jointly considering their corresponding reviews. However, these features are only reivew-driven and may not be comprehensive. Hence, an interaction-based learning component further extracts complementary features from interaction data alone, also on the basis of user-item pairs. The final rating score is then derived with a dynamic linear fusion mechanism. Experiments on seven real-world datasets show that CARL achieves significantly better rating prediction accuracy than existing state-of-the-art alternatives. Also, with the attention mechanism, we show that the pair-based relevant information (i.e., context-aware information) in reviews can be highlighted to interpret the rating prediction for different user-item pairs.

In the past few years, internet of things has been explored in medical area to achieve high efficiency and accuracy in the medical treatment and management. One of the most powerful technologies called the medical Internet of Things (mIoT), is underpinned by the considerable computational ability of cloud and the efficient data collection of medical sensors. As the data is transmitted over open network, security remains a paramount concern in mIoT. Encryption techniques may help to protect patient privacy, but they limit the future retrieval of the encrypted data. To uplift this limitation, public key encryption with keyword search (PEKS) has been introduced. However, most of the existing PEKS schemes are based on public key infrastructure or identity-based cryptography, which suffers from the certificate management issue and key escrow problem in system deployment, respectively. Moreover, inside keyword guessing attack seems to become a severe issue to violate privacy in data search. To address these issues, we present a certificateless searchable public key authenticated encryption scheme with designated tester (CL-dPAEKS), which, we believe, is suitable for cloud-assisted mIoT. We prove that our scheme can resist various types of attacks, and it is more secure than other schemes that built on certificateless cryptography, without significant loss in efficiency.

The Internet of Things is one of the new emerging application domains that require delay tolerant network (DTN) support, where an end-to-end path between the source and the destination may not always exist. Due to the intermittent connectivity of DTN, the design of an efficient routing algorithm is the main challenge. In this paper, we first define a metric called message handling capacity to determine the ability of a node to forward messages. Then, we introduce a concept called connection strength to reflect the connection time between nodes and then integrate the concept into delivery predictability used by Prophet to determine the chance of a node completely delivering a message to the destination. Subsequently, we present a metric called quality of node (QoN), which is calculated by combining the relative weights of the message handling capacity and the improved delivery predictability. Finally, we present an adaptive spray and wait routing algorithm based on QoN (QoN-ASW). The QoN-ASW adaptively allocates the number of message copies between the encountered nodes according to the proportion of quality of node in the spray phase, which avoids the blindness of replica distribution. In addition, a forwarding scheme is implemented in the wait phase, which takes full advantage of encounter opportunities. In the simulation, we demonstrate the efficiency of integrating the connection strength into delivery predictability and compare the QoN-ASW with four existing DTN routing algorithms from four aspects. The simulation results show that the QoN-ASW can significantly improve the delivery rate and reduce the average delay while achieving a relatively low overhead.

In this paper, we propose a novel ant colony optimization algorithm based on improved brainstorm optimization (IBSO-ACO) to solve the vehicle routing problem with soft time windows. Compared with the traditional ant colony algorithm, the proposed IBSO-ACO can better address the local optimum problem, since we have carefully designed an improved brainstorming optimization algorithm to update the solutions obtained by the ant colony algorithm, which enhance the solution diversity and the global search ability. Furthermore, we use the classification method to accelerate the convergence of the proposed algorithm. The extensive experimental results have confirmed that the proposed IBSO-ACO algorithm can achieve a lower routing cost at a high convergence rate than the traditional ant colony algorithm and the simulated annealing ant colony algorithm.

Storage of endoscopy images poses a great problem in the health sector, and to our best knowledge, the limited study focuses on the identified problem. In this study, a system developed specifically to detect lesions and automatically save them employed to reduce the size of endoscopy images and videos. 5,460 images were collected for training to detect lesions, YOLO (You Only Look Once) V3 (version 3) which is a deep convolutional neural network was introduced to detect gastritis lesions from different parts of the stomach. A deep convolutional neural network that is a powerful model used to assist in classifying endoscopy images accuracy. 114,657 images were trained on the ResNet-50 model for the distribution of image classification. The proposed method achieved a sensitivity, specificity, and accuracy of 91%, 94%, 97%. If trained further with the dataset, it could become a complementary tool for patient management. The proposed method was able to achieve an automated system that is able to retain images of detected lesions at reduced storage can be used in endoscopy centers.

The introduction of a lightweight encryption scheme in the vehicular network has improved the reliability and security of data transmission substantially among vehicles. However, it is still not guaranteed that all vehicles comply with the encryption scheme throughout the whole operation period, considering the inherent selfishness of each participant. Apart from that, the data scheduling issue is another major concern in the vehicular network due to the high-speed mobility of vehicles. To tackle these issues, a multi-objective and multi-dimensional incentive mechanism is developed in this paper to achieve privacy-aware data scheduling for vehicles. This mechanism is designed to encourage vehicles to carry out different tasks by providing relevant incentives while maximizing the overall utility of the network. Additionally, security and privacy of data transmission between vehicles and cloud servers are realized through a data perturbation approach. Experimental evaluation shows that the proposed incentive mechanism is better than the traditional methods when it comes to maximizing the number of participants and completed key tasks.

Non-Volatile Memory (NVM) technologies, such as Phase Change Memory (PCM), herald the next generation of main memory as they offer superior features compared with DRAM. Unfortunately, NVM's limited write endurance hinders its adoption as its lifetime can be extremely short under skew writes. This paper observes that the loops in programs are one of the primary causes of uneven writes as they introduce the hot data and cause a large number of stack frames to be allocated to the same locations. To alleviate this problem, we present Loop2Recursion, a compile-time wear leveling technique for transforming loops into recursions automatically. Our approach is flexible as it can avoid a substantial memory overhead by limiting the depth of recursion. Experimental results demonstrate that Loop2Recursion can significantly improve the wear leveling over stack area compared to the state-of-the-art methods, while incurring only negligible performance overhead.

Recent advances in cloud storage have enabled users to outsource large amounts of data to a remote cloud server in order to reduce storage and management costs, and share files among many users in a group. However, how to efficiently audit the integrity of shared data while maintaining data privacy and user identity anonymity, is still a critical issue. We propose a novel public auditing scheme for data stored in a remote cloud server and shared among users in a large group. In particular, the proposed scheme incorporates group signature, homomorphic message authentication code to create data block tags, so that it can support public auditing and provide user identity anonymity. Furthermore, we use the random masking technique in the proposed scheme to preserve data privacy from the third-party auditor. The correctness and security analyses demonstrate that the proposed scheme is correct and provably secure under a robust security model. The performance evaluation and experimental results show that the proposed scheme is efficient while maintaining the desirable security properties.

In the area of searchable encryption, the searchable public key encryption (SPE) is an attractive technique in secure cloud storage. SPE assures the data confidentiality without affecting the usage of the data stored in the cloud. Furthermore, compared with the symmetric searchable encryption, SPE does not require key distribution and management. We investigate the security of the searchable public key encryption based on the traditional Boneh’s framework. Although existing SPE schemes can enable users to search over encrypted data, most of these schemes are vulnerable to the file-injection attack and the insider keyword guessing attack. To mitigate these attacks, we propose an efficient and secure searchable public key encryption with privacy protection (SPE-PP). We then provide a concrete construction of SPE-PP that uses the Diffie–Hellman shared secret key, and we prove it can resist these attacks. Both the theoretical analysis and the experimental results show that our scheme achieves strong security along with high efficiency.

Wireless body area networks (WBANs) consist of many small low-power sensors, through which users could monitor the real-time parameters of patients' physiology remotely. This capability could improve medical care and the monitoring of patients. WBAN devices typically have limited computing, storage, power, and communication capabilities. These limitations restrict the applications that WBANs can support. To enhance the capabilities of WBANs, the concept of cloud-assisted WBANs has been introduced recently. By using cloud computing technologies, cloud-assisted WBANs can provide more efficient processing of patients' physiology parameters and support richer services. In cloud-assisted WBANs, the data of patients' physiology are stored in the cloud. The integrity of the data is very important because these data will be used to provide a medical diagnosis and other medical treatments. To address the issue of integrity in cloud-assisted WBANs, we propose an efficient certificateless public auditing (CLPA) scheme. A security analysis of our proposed CLPA scheme shows that it is provably secure against two types of adversaries (i.e., a type-I adversary can replace users' public keys, and a type-II adversary can access the master key) in an environment of certificateless cryptography. A detailed performance analysis demonstrates that the proposed CLPA scheme yields better performance over a previously proposed CLPA scheme.

Wearable devices, e.g., smart glass and watch, could achieve fine-grained human-centric sensing nowadays, but still lack sufficient capacities to execute sophisticated data processing algorithms. This paper presents Outlet to explore the feasibility to leverage the available computing resources from user’s ambience, e.g., from nearby smart phones, tablets, computers, Wi-Fi APs, and so on, to form a mobile computing edge. We can then outsource wearable computing tasks to this ambient edge to locally digest the sensory data for prompt user feedback and reaction, as it is perfectly located in user’s vicinity. The Outlet design avoids the traditional offloading to the remote clouds, whose performance may highly depend on the high-speed Internet connectivity and availability. To enable the Outlet design, we identify three major challenges: context dependence, scattered resources, and resource dynamics, and propose a series of key techniques to address each of them. To examine Outlet ’s performance, we conduct extensive trace-driven evaluations and the results indicate promising performance achieved by Outlet , e.g., mostly within 97.6% to 99.5% closeness of the optimal performance and always outperforming the baseline approach under various system settings.

The stable and fair data transmission of vehicular networks can improve transport efficiency and reduce traffic accident. It is challenging to ensure the stability and fairness of data transmission in dynamic vehicular networks. However, existing works based on opportunistic scheduling cannot support reliable transmission since stability and fairness are difficult to be guaranteed at the same time. In this paper, we propose a stable scheduling scheme for dynamic vehicular networks based on fair allocation of available channel resources. We formulate the problem of stability and fairness as network utility maximization, and propose an algorithm, called SF-NUM, to solve it. SF-NUM uses the stability scheduling method based on back pressure vector for the first time in vehicular networks. In order to achieve the fairness distribution of channel resources of the vehicular networks in the distributed computing way, multiple factors are considered in the SF-NUM algorithm. The experimental results show that the proposed algorithm outperforms other algorithms.

The handover authentication protocol plays an important role in mobile wireless networks where mobile devices often need to securely and seamlessly roam among different access points. To satisfy various security and privacy requirements of practical wireless applications, many handover authentication protocols for mobile wireless networks have been proposed in the last decade. In particular, the handover authentication protocol using the Identity-based Public Key Cryptography (ID-based PKC) has better security and has attracted a lot of attention recently. Here, we discuss the security and privacy requirements of handover authentication protocols for mobile wireless networks and we present a brief review of handover authentication protocols using the ID-based PKC technique. Our security analysis shows that only one of the recent protocols proposed can satisfy all security and function requirements. We also implement and compare the communication and computation costs associated with these protocols on a specific mobile device.

Public verification of data integrity is crucial for promoting the serviceability of cloud storage systems. Recently, Tan and Jia (2014) proposed an identity-based public verification (NaEPASC) protocol for cloud data to simplify key management and alleviate the burden of check tasks. They claimed that NaEPASC enables a third-party auditor (TPA) to verify the integrity of outsourced data with high efficiency and security in a cloud computing environment. However, in this paper, we pinpoint that NaEPASC is vulnerable to the signature forgery attack in the setup phase; i.e., a malicious cloud server can forge a valid signature for an arbitrary data block by using two correct signatures. Moreover, we demonstrate that NaEPASC is subject to data privacy threats in the challenge phase; i.e., an external attacker acting as a TPA can reveal the content of outsourced data. The analysis shows that NaEPASC is not secure in the data verification process. Therefore, our work is helpful for cryptographers and engineers to design and implement more secure and efficient identity-based public auditing schemes for cloud storage.

Designing an efficient and secure authentication scheme to ensure secure communication between parties in an ad hoc network remains challenging. Recently in 2017, Shaghayegh and Mehdi proposed an identity-based authentication scheme using bilinear pairings for Ad hoc networks. The scheme is claimed to be secure against a number of known attacks and provides non-repudiation property not found in most other authentication protocols. However, we demonstrate that their scheme is vulnerable to man-in-the-middle and forgery attacks, two previously unknown flaws. We then propose an improved mutual authentication scheme based on identity-based encryption (IBE) for Ad hoc networks. Our security analysis and experimental results demonstrate that the proposed scheme is secure and highly efficient.

Efficient searching on encrypted data outsourced to the cloud remains a research challenge. Identity-based encryption with equality test (IBEET) scheme has recently been identified as a viable solution, in which users can delegate a trapdoor to the server and the server then searches on user outsourced encrypted data to determine whether two different ciphertexts are encryptions of the same plaintext. Such schemes are, unfortunately, inefficient particularly for deployment on mobile devices (with limited power/battery life and computing capacity). In this paper, we propose an efficient IBEET scheme with bilinear pairing, which reduces the need for time-consuming HashToPoint function. We then prove the security of our scheme for one-way secure against chosen identity and chosen ciphertext attacks (OWIDCCA) in the random oracle model (ROM). The performance evaluation of our scheme demonstrates that in comparison to the scheme of Ma (2016), our scheme achieves a reduction of 36.7% and 39.24% in computation cost during the encryption phase and test phase, respectively, and that our scheme is suitable for (mobile) cloud deployment. We propose an identity-based encryption with equality test (IBEET) scheme using bilinear pairing for cloud storage.We show that our proposed concrete scheme is provably secure. It satisfies required security properties.Detailed performance analysis and experimental result are given.

In the smart city construction, massive data collected from various fields need to be outsourced to the cloud for convenience and resource saving. However, integrity and confidentiality of the data in cloud remains a challenge issue due to the loss of data possession. As a solution, some public data auditing schemes have been proposed in last several years. Most recently, Li et al. proposed an efficient public auditing scheme and claimed that it could reduce the cost of clients on generating verification metadata. In this paper, we analyze the security of Li et al.'s scheme and point out two weaknesses in it. We demonstrate that it cannot achieve the confidentiality for outsourced data and it is vulnerable to the proof forgery attack. To address these weaknesses, we propose an improved public auditing scheme, which can not only preserve the data privacy but also resist the proof forgery attack. Security analysis shows that our scheme is provably secure in a robust security model. Performance analysis shows that the proposed scheme can overcome the weaknesses in Li et al.'s scheme at the cost of increasing computation overhead slightly.

Cloud storage is widely used by both individual and organizational users due to the many benefits, such as scalability, ubiquitous access, and low maintenance cost (and generally free for individual users). However, there are known security and privacy issues in migrating data to the cloud. To ensure or verify data integrity, a number of cloud data integrity checking schemes with different properties have been presented in the literature. Most existing schemes were subsequently found to be insecure or have high computation and communication costs. More recently in 2016, Yu et al. (Future Gener Comput Syst 62:85–91, 2016) proposed an identity-based auditing scheme for checking the integrity of cloud data. However, in this paper, we reveal that the scheme is vulnerable to data recovery attack. We also present a new identity-based public auditing scheme and formally prove the security of the scheme under the RSA assumption with large public exponents in the random oracle model. We then evaluate the performance of our proposed scheme and demonstrate that in comparison with Yu et al.'s scheme, our proposal is more practical in real-world applications. Refereed/Peer-reviewed

Black-burst based multi-hop broadcast protocols are effective means to disseminate Emergency messages (EMs) in Vehicular ad hoc networks (VANETs). However, Clear to broadcast (CTB) collision will happen and reduce propagation speed. Aiming at this problem, we propose a Black-burst and multi-channel based multihop broadcast (BMMB) protocol. Vehicles with multiple antennas can transmit and sense black-burst at different channels simultaneously based on multi-channel technology. Compared with existing black-burst based methods, BMMB shortens the iterative procedure to find out the optimal segment. Only one relay vehicle can be rapidly selected within the optimal segment without CTB collision. BMMB enables alternative broadcast methods, i.e., unidirectional broadcast and multi-directional broadcast for straight roads and intersections respectively. Theoretical analysis is done for performance evaluation of BMMB, and simulation results demonstrate that BMMB performs better in terms of average one-hop delay and propagation speed.

As an essential technology of cloud computing, the cloud storage can exactly satisfy the demand of users with the service of scalability, ubiquitous access and low maintenance cost. However, moving data to the cloud servers will bring some significant security challenges due to the loss of the physical data possession. In order to verify the data integrity, many verifiable data possession schemes have been proposed in last several years. Very recently, Tang and Zhang proposed a new publicly verifiable data possession (PVDP) scheme for remote storage. They claimed that their scheme was suitable for checking the storage correctness and secure against various types of attacks. In this paper, we analyze the security of Tang and Zhang’s PVDP scheme and prove that it is vulnerable to the data recovery attack. We also demonstrate that PVDP scheme works incorrectly with a concrete instance. Our analysis shows that their scheme is not suitable for practical applications. Our work can help cryptographers and engineers design and implement more secure and efficient public auditing schemes for the cloud storage data.