Federated learning (FL) improves privacy by training models on local devices and only exchanging updates with the central server. Vehicular Edge Computing (VEC) uses FL to improve model accuracy while preserving data privacy. FL keeps sensitive data, such as location information, driving behavior, on local devices. Instead of raw data, vehicles collaboratively share model updates, which reduces the risk of data leakage and exposure. However, FL is vulnerable to model poisoning attacks, especially when privacy measures hide updates and restrict central server monitoring. Existing defenses, such as robust aggregation, are often insufficient or computationally expensive. To address these challenges, we propose RepuChainFL, a decentralized framework that makes federated learning more secure and trustworthy. The system rewards reliable and honest participants(vehicles) using blockchain and a Proof-of-Work contribution approach using Trust Tokens (TRST). Each vehicle is given a unique identity, which eliminates the risk of duplicate and fake identities. The model updates are validated by a group of selected participants using methods like cosine similarity and local performance testing. All updates, results, and decisions are stored on the blockchain, ensuring transparency throughout the system. RepuChainFL provides a reliable and scalable solution using federated learning in connected and safety-critical vehicle networks.

While several commercial software packages for simulating the dynamics of robot or human-ridden Single-Track Vehicles (STV s) such as bicycles, motorcycles, or other Powered Two-Wheelers (PTWs) are common in the literature, open-source options for high-fidelity simulations of STV dynamics are limited. This paper explores whether the open-source Webots robot simulator is capable of representing the dynamics of STV s with sufficient fidelity to allow for robotic rider design. Data from a small-scale self-balancing PTW are compared with both a linear dynamic model and with simulation results from a nonlinear, multi-body model of the vehicle custom-built in Webots. Results indicate that Webots's physics engine provides sufficient dynamic fidelity to accurately represent the behavior of the vehicle in both simple step response tests and in assisted teleoperation with automatic starting and stopping via a motorized kickstand.

Motorcycles, bicycles, and other single-track vehicles are popular but dangerous methods of transportation. While some are piloted by only a single rider, many powered two-wheelers are ridden with a passenger, who may also significantly influence the vehicle's dynamics. Because simulations are a critical component of vehicle safety research, this paper asks whether a simulated, active “virtual passenger” has stabilizing or destabilizing effects on a rider-vehicle-passenger system. This virtual passenger exerts its control effort by moving an inverted pendulum to simulate the motion of a human passenger's torso without explicit knowledge of rider inputs. A battery of simulations in the nonlinear, multi-body Webots robot simulator show that the passenger's control efforts have mixed effects on both rider effort and vehicle stability over abrupt transitions in pavement height. This indicates that the inclusion of passenger motion may be critical when vetting the safety of roadway designs and/or emerging motorcycle technologies like Advanced Rider Assist Systems.

This work introduces a dual-channel digital-to-time converter (DTC) featuring a broad tuning range, which utilizes a dual delay-locked loop (DLL) architecture to achieve clock or data deskewing and precise timing adjustment effectively. The coarse- and fine-tuning mechanisms are operated in precise closed-loop schemes to lessen the effects of the ambient variations. The replica fine voltage-controlled delay line can provide subgate resolution and instantaneous switching capability. Then, the replica coarse voltage-controlled delay line can provide a wide dynamic delay range. The proposed DTC can generate variable delays for an arbitrary pseudorandom data rate of up to 3 Gb/s and is insensitive to process and temperature variation. The test chip, fabricated in a 55-nm CMOS process, operates from 0.05 to 1.5 GHz and achieves a timing resolution of 9.77 ps, a power consumption of 12 mW, and an area of 0.76 mm2. The measured maximum integral nonlinearity (INL) is 2.20 LSB in an extended delay mode. In the dual delay mode, the maximum INL of channels 0 and 1 is 1.60 and −1.08 LSB, respectively.

The Controller Area Network (CAN) is the most widely used protocol for data transmission in in-vehicle networks. However, the lack of a robust security scheme makes it vulnerable to various cyber-attacks, posing significant threats to automotive functional safety. The limited computing resources of Electronic Control Units (ECUs), restricted network bandwidth, and high real-time requirements make it challenging to apply conventional encryption and authentication mechanisms. This paper proposes a lightweight secure communication scheme using encryption and authentication based on Physically Unclonable Function (PUF) technology. We first designed a ring oscillator PUF with a multi-loop comparison circuit (MLC-ROPUF) suitable for in-vehicle networks with constrained resources. The MLC-ROPUF is used to generate key parameter for the lightweight encryption algorithm Salsa20, which is applied to distribute shared key parameters to different ECUs. After receiving the CAN message, ECU utilizes the output response of MLC-ROPUF to generate the key stream of Salsa20 and decrypt the data segment of the CAN message, obtain the shared key parameters. The SM3 algorithm is then utilized to generate shared keys for confidential communication based on the obtained key parameters. Simultaneously, ECU identity authentication is completed to reduce communication costs. To validate the proposed scheme, we conducted experiments on a designed prototype system, and the results show that the proposed method performs well in terms of resource consumption and real-time capabilities.

The rapid evolution of Internet of Vehicles (IoVs) technologies has ushered in an era of connected transportation, which has enabled us to collect and analyze data at an unprecedented scale. However, the vast amount of data generated by IoVs poses significant privacy and security challenges, as they may be susceptible to leakage and manipulation by malicious attackers. In this work, we explore the integration of emerging blockchain technology with federated learning to create a secure and decentralized framework for IoV data management and analysis. The proposed system leverages the immutable and transparent nature of blockchain to ensure data integrity and trust among IoV nodes, while federated learning facilitates collaborative machine learning without compromising individual data privacy. Through a combination of cryptographic techniques and consensus mechanisms, the blockchain-enabled federated learning system aims to thwart adversarial attacks, ensure secure data aggregation, and enhance the overall resilience of IoV networks. This study presents a comprehensive architecture, evaluates its performance through simulations, and demonstrates its potential in mitigating security risks in IoV environments. The findings highlight the feasibility and effectiveness of this approach, paving the way for more robust and secure IoV systems.

This paper presents the design and implementation of a systematic Inter-Component Communications (ICCs) dynamic Analysis Technique (SIAT) for detecting privacy-sensitive data leak threats. SIAT’s specific approach involves the identification of malicious ICC patterns by actively tracing both data flows and implicit control flows within ICC processes during runtime. This is achieved by utilizing the taint tagging methodology, a technique utilized by TaintDroid. As a result, it can discover the malicious intent usage pattern and further resolve the coincidental malicious ICCs and bypass cases without incurring performance degradation. SIAT comprises two key modules: Monitor and Analyzer. The Monitor makes the first attempt to revise the taint tag approach named TaintDroid by developing the built-in intent service primitives to help Android capture the intent-related taint propagation at multi-level for malicious ICC detection. Specifically, we enable the Monitor to perform systemwide tracking of intent with five abstraction functionalities embedded in the interactive workflow of components. By analyzing the taint logs offered by the Monitor, the Analyzer can build the accurate and integrated ICC patterns adopted to identify the specific leak threat patterns with the identification algorithms and predefined rules. Meanwhile, we employ the patterns’ deflation technique to improve the efficiency of the Analyzer. We implement the SIAT with Android Open Source Project and evaluate its performance through extensive experiments on a particular dataset consisting of well-known datasets and real-world apps. The experimental results show that, compared to state-of-the-art approaches, the SIAT can achieve about 25% ∼200% accuracy improvements with 1.0 precision and 0.98 recall at negligible runtime overhead. Apart from that, the SIAT can identify two undisclosed cases of bypassing that prior technologies cannot detect and quite a few malicious ICC threats in real-world apps with lots of downloads on the Google Play market.

The proliferation of IoT and CPS technologies demand novel conceptual, foundational and applied cybersecurity solutions. The dynamic behaviour of these distributed systems augmented with physical and computational constraints of smart devices, require cybersecurity approaches for timely prevention and detection of attacks. This panel aims to discuss open challenges and highlight future research directions for cybersecurity in IoT and CPS.

The physical layer secret key generation scheme is a preferred solution designed for resource-constrained Internet of Things (IoT) devices. But it suffers from a severe attack, the signal manipulating attack, which aims at controlling the generated key. The existing solutions either cannot prevent all kinds of signal manipulation attacks or require working in full-duplex mode, which is not suitable for resource-constrained IoT devices. In this article, we introduce a secret key generation scheme with the help of an untrusted relay to address this dilemma. Also, our method can protect the privacy of legitimate users from the untrusted relay. We conclude a general signal manipulation attack model from existing practical signal manipulation attacks and analyze the security strength and privacy preserving ability of our scheme based on this model. Finally, we compare our method with existing signal manipulation attack solutions. The result shows that our method is the best solution for resource-constrained IoT systems.

Physical unclonable functions (PUFs) have been adopted in many resource-constrained Internet of Things (IoT) applications to provide effective and lightweight solutions for device authentication. However, an attacker can collect challenge–response pairs (CRPs) of a strong PUF, to build a machine learning (ML) model and mimic its behavior, i.e., predicting the responses of unseen challenges with high accuracy. Although several PUFs have been proposed to resist such modeling attacks, they incur high hardware overhead. Developing a PUF primitive with low hardware cost and high resistance to ML attacks is thus a crucial task. In this article, we propose the first response–feedback-based lightweight anti-ML-attack PUF (FLAM-PUF). It is only composed of one arbiter PUF (APUF) and one Galois linear-feedback shift register (LFSR), with some basic logic gates, reducing more than 62% hardware cost compared with the state-of-the-art robust strong PUFs. Specifically, FLAM-PUF leverages a cost-effective feedback loop structure to dynamically control and update the LFSR configuration. FLAM-PUF has two main characteristics: 1) it feeds back a 1-bit response in every cycle to intentionally poison the data of the CRP set for training. To resist ML-based modeling attacks, the 1-bit response can randomly update one coefficient of the feedback polynomial to implant more complex correlations into the model built by attackers and 2) it takes advantage of an$n-$bit response feedback-controlled reconfigurable Galois LFSR to enlarge the original challenge space of the APUF. Extensive experimental results show that the proposed FLAM-PUF achieves near-optimal uniformity, uniqueness, and reliability. Our scheme works well under standard attack models with public crucial initial information. In particular, the prediction accuracy of modeling attacks against FLAM-PUF is nearly 50% under the four widely used ML algorithms, i.e., support vector machines (SVMs), logistic regression (LR), covariance matrix adaptation evolution strategy (CMA-ES), and deep neural networks (DNNs), indicating excellent resistance against these ML attacks.

Currently, connected vehicles have gradually stepped into our daily lives, and they generally rely on vehicular networks to generate and exchange traffic-related messages to improve the overall travel safety and efficiency. However, due to the open nature of vehicular networks, these traffic-related messages could be erroneous, which may be caused by various reasons, ranging from an onboard device (OBD) sensor malfunctioning and reporting incorrect reading to the message being tampered by a malicious vehicle. To address these rapidly increasing security challenges, we have proposed an AI-enabled trust management system (AIT) in this article, which is an AI-enabled trust management system for vehicular networks using the blockchain technique. In the AIT system, each vehicle first senses, generates, and exchanges messages with other vehicles. These messages then get validated by the neighboring vehicles. As vehicles receive and validate messages from other nearby vehicles, they will establish and manage the trust of those nearby vehicles, which is enabled by utilizing the deep learning algorithm. Once a vehicle identifies untrustworthy vehicles, it reports them to the nearby roadside unit (RSU), and the RSU will validate the authenticity of the report as well as the identity of the vehicle by using the emerging blockchain technique. The security credentials of untrustworthy vehicles will then be revoked by the RSU. We have conducted an extensive experimental study to evaluate the AIT system. Simulation results clearly indicate that AIT performs better than existing approaches and can manage the trust of vehicles and detect malicious ones in an accurate and efficient manner.

In recent years, erasure codes have become the de facto standard for data protection in large scale distributed cloud storage systems at the cost of an affordable storage overhead. However, traditional erasure coding schemes, such as Reed-Solomon codes, suffer from high reconstruction cost and I/Os. The recent past has seen a plethora of efforts to optimize the tradeoff between the reconstruction cost, I/Os and storage overhead. Quiet different from all prior studies, in this paper, our erasure coding technique makes the first attempt to take advantage of the unequal failure rates across the disks/nodes to optimize the system reliability and reconstruction performance. Specifically, our proposed technique, the Unequal Failure Protection based Local Reconstruction Code (UFP-LRC) divides the data blocks into several unequal-sized groups with local parities, assigning the data blocks stored on more failure-prone disks/nodes into the smaller-sized group, so as to provide unequal failure protection for each group. In this way, by exploiting the nonuniform local parity degrees, the proposed UFP-LRC enables the data blocks that are stored on more failure-prone disks/nodes to tolerate a greater number of failures while suffering from less repair cost than others, leading to a substantial improvement of the overall reliability and repair performance for cloud storage systems. We perform numerical analysis and build a prototype storage system to verify our approach. The analytical results show that the UFP-LRC technique gradually outperforms LRC along the increase of failure rate ratio. Also, extensive experiments show that, when compared to LRC, UFP-LRC is able to achieve a 10 to 15 percent improvement in throughput, and an 8 to 12 percent reduction in decoding latency, while retaining a comparable overall reliability.

Summary Human contact prediction is a challenging task in mobile social networks. The existing prediction methods are based on the static network structure, and directly applying these static prediction methods to dynamic network prediction is bound to reduce the prediction accuracy. In this paper, we extract some important features to predict human contacts and propose a novel human contact prediction method based on naive Bayes algorithm, which is suitable for dynamic networks. The proposed method takes the ever‐changing structure of mobile social networks into account. First, the past time is partitioned into many periods with equal intervals, and each period has a feature matrix of all node pairs. Then, with the feature matrixes used for classifiers training based on naive Bayes algorithm, we can get a classifier for each time period. At last, the different weights are assigned to the classifiers according to their importance to contact prediction, and all classifiers are weighted combination into the final prediction classifier. The extensive experiments are conducted to verify the effectiveness and superiority of the proposed method, and the results show that the proposed method can improve the prediction accuracy and TP Rate to a large extent. Besides, we find that the size of time interval has a certain impact on the clustering coefficient of mobile social networks, which further affects the prediction accuracy.

In the fifth generation mobile networks(5G), D2D (device-to-device) communication technology is introduced to provide services to users by utilizing the resources of idle mobile devices, and users can schedule computing tasks to be executed on mobile servers (MSs). This paper aims at reducing overall time delay and energy consumption by taking into account MSs mobility, task attributes, resource status for D2D scenario. We formulate the matching problem as a one-to-one matching game and propose a scheduling strategy based on binary graph matching algorithm. Simulations show that the strategy proposed in this paper can comprehensively reduce the task execution delay and energy consumption, and improve the success rate of task execution.

In the edge computing, the service is deployed to the edge server through virtualization technology. Most strategies of service deployment are singleness and ignore the diversity of users' requirements and the service deployment cost at the edge. This paper proposes a clustering-based algorithm for service deployment, which considers the delay at the user side and the edge-side services deployment cost, and establishes a service deployment model based on multi-objective integer linear programming. Firstly, the K-means clustering algorithm is optimized to solve the problem of hotspot migration in the process of service deployment and reduce the deployment cost at the edge server side, then alternative enhanced heuristic algorithm is proposed to find the approximate optimal solution of services deployment. Experiments show that the algorithm can reasonably deploy services. Compared with traditional heuristic algorithms, the algorithm proposed in this paper has better performance in terms of user side and edge server side.

In[1], the financial support information in the first footnote should have read as follows.

With the emergence of computation-intensive applications such as face recognition, natural language processing, etc., the performance of mobile devices appears to be weak. Mobile cloud computing is extensively used to cover the aforementioned shortage. However, the distance between remote cloud and mobile devices might be too far to be tolerable. Cloudlet computing, fog computing, and mobile edge computing are proposed to bring the computing resources near to the mobile devices to reduce the high delay caused by the long distance. Although there exist tremendous studies focused on the offloading strategies, where and how to place edge servers to minimize the edge server providers' cost is seldom involved. In this paper, we first investigate the problem of minimizing the number of edge servers while ensuring QoS constraints such as access delay, and the Integer Linear Programming (ILP) formulation of this problem is given. Then, we transform it into the minimum dominating set problem of graph theory and propose a greedy algorithm to solve it. The simulation results demonstrate the proposed algorithm is promising.

The Internet of Things (IoT), which is known as one of the key enabling technologies of smart cities, generally refers to the network of smart objects, which are embedded with sensing, computing, networking, and actuating capabilities that all together enable them to collect and exchange data. The IoT devices are usually wirelessly networked, and they serve as a key enabling technology for many critical smart city applications, such as intelligent transportation, smart grid, smart building, and mobile healthcare. However, security has become a key challenge for the wide deployment of IoT: because of the environmental influences, the IoT data are inherently noisy. Moreover, the IoT devices may be compromised by attackers to intentionally generate fake data. Finally, the underlying wireless network can also be subverted. To address the security issue in IoT, we propose a policy-based secure and trustworthy sensing scheme for IoT named RealAlert, in which the trustworthiness of both data and the IoT devices are evaluated based on both the reporting history and the context in which the data are collected using policy rules. Experimental results have shown that the RealAlert scheme can accurately assess the trust of the sensor nodes as well as data in IoT.

Cyberspace is the most popular environment for information exchange whose security suffers from ever-increasing chal-

While the online social network (OSN) has brought much convenience to users, there are still some serious problems, such as personal privacy leaks. Today, OSN security and privacy protection are one of the most important focuses of the research. In this paper, we present an intelligent privacy protection approach to solve problems of security and privacy protection in OSNs. First, the proposed algorithm combines a neural network with a hybrid hierarchy genetic algorithm and radial basis function, which is used to construct a prediction model of OSN security. Then, a support vector machine is applied to preprocess information of the OSN, and the attribute-based encryption scheme is adopted to encrypt the OSN information. Finally, a particle swarm optimization algorithm is used to improve OSN security and privacy protection. The experimental results demonstrate the effectiveness of the proposed method.

The television audience rating is an important indicator of the quality of television programs and important reference for decision-television operator. As many factors that affect the ratings and the trends are complex, the article proposes a television rating mining predictive model based on fuzzy cognitive maps (FCMs) with forward stepwise regression. The FCMs use the causal relationship among various concept nodes to simulate the fuzzy reasoning, and enhance the dynamic behavior of the simulation system with its feedback mechanism, which is suitable for system to predict the trend of television audience rating. A FCM-based model for predicting television audience rating is proposed in this paper. The forward stepwise regression algorithm is used to obtain concept nodes of coarse weight matrix for FCMs, and then a training weight algorithm is used to refine the coarse weight matrix model. The FCM model is applied to mine the television audience rating, realizing to predict the television playback volume. The experimental result shows that the modeling method is effective.

In recent years, Android malware has continued to grow at an alarming rate. More recent malicious apps’ employing highly sophisticated detection avoidance techniques makes the traditional machine learning based malware detection methods far less effective. More specifically, they cannot cope with various types of Android malware and have limitation in detection by utilizing a single classification algorithm. To address this limitation, we propose a novel approach in this paper that leverages parallel machine learning and information fusion techniques for better Android malware detection, which is named Mlifdect. To implement this approach, we first extract eight types of features from static analysis on Android apps and build two kinds of feature sets after feature selection. Then, a parallel machine learning detection model is developed for speeding up the process of classification. Finally, we investigate the probability analysis based and Dempster-Shafer theory based information fusion approaches which can effectively obtain the detection results. To validate our method, other state-of-the-art detection works are selected for comparison with real-world Android apps. The experimental results demonstrate that Mlifdect is capable of achieving higher detection accuracy as well as a remarkable run-time efficiency compared to the existing malware detection solutions.

In recent years, erasure codes have become the de facto standard for data protection of large scale distributed cloud storage systems at the cost of an affordable storage overhead. While traditional erasure coding schemes, such as Reed-Solomon codes, suffer from high reconstruction cost and I/Os. The recent past has seen a plethora of efforts to optimize the tradeoff between the reconstruction cost, I/Os and storage overhead. Quietly different from all prior studies, in this paper, our erasure coding technology makes the first attempt to take advantage of the unequal failure rates across the disks/nodes to optimize the reconstruction performance and system reliability. Specifically, our proposed technology, the Unequal Failure Protection based Local Reconstruction Code (UFP-LRC) divides the data blocks into several unequal-sized groups with local parities, assigning the data blocks stored on more failure-prone disks/nodes into the smaller-sized group, so as to provide unequal failure protection for each group. In this way, by exploiting the nonuniform local parity degrees, the proposed UFP-LRC enables the data blocks that are stored on more failure-prone disks/nodes to tolerate a greater number of failures while suffer from less repair cost than others, leading to a substantial improvement of overall repair performance and reliability for cloud storage system. We perform numerical analysis and build a prototype storage system to verify our approach. The analytical results show that the UFPLRC technique gradually outperforms LRC along the increase of failure rate ratio. Also, extensive experiments show that, when compared to LRC, UFP-LRC is able to achieve a 10% to 13% improvement in throughput, and a 8% to 12% reduction in decoding latency, while retaining a comparable overall reliability.

The legitimate driver of a vehicle traditionally gains authorization to access their vehicle via tokens such as ignition keys, some modern versions of which feature RFID tags. However, this token-based approach is not capable of detecting all instances of vehicle misuse. Technology trends have allowed for affordable and efficient collection of various sensor data in real time from the vehicle, its surroundings, and devices carried by the driver, such as smartphones. In this paper, we propose to use this sensory data to actively identify and authenticate the driver of a vehicle by determining characteristics which uniquely categorize individuals' driving behavior. Our approach is capable of continuously authenticating a driver throughout a driving session, as opposed to alternative approaches which are either performed offline or as a session starts. This means our modeling approach can be used to detect mid-session driving attacks, such as carjacking, which are beyond the scope of alternative driver authentication solutions. A simulated driving environment was used to collect sensory data of driver habits including steering wheel position and pedal pressure. These features are classified using a Support Vector Machine (SVM) learning algorithm. Our pilot study with 10 human subjects shows that we can use various aspects of how a vehicle is operated to successfully identify a driver under 2.5 minutes with a 95% confidence interval and with at most one false positive per driving day.

Vehicular ad hoc networks (VANETs) have the potential to transform the way people travel through the creation of a safe interoperable wireless communications network that includes cars, buses, traffic signals, cell phones, and other devices. However, VANETs are vulnerable to security threats due to increasing reliance on communication, computing, and control technologies. The unique security and privacy challenges posed by VANETs include integrity (data trust), confidentiality, nonrepudiation, access control, real-time operational constraints/demands, availability, and privacy protection. The trustworthiness of VANETs could be improved by addressing holistically both data trust, which is defined as the assessment of whether or not and to what extent the reported traffic data are trustworthy, and node trust, which is defined as how trustworthy the nodes in VANETs are. In this paper, an attack-resistant trust management scheme (ART) is proposed for VANETs that is able to detect and cope with malicious attacks and also evaluate the trustworthiness of both data and mobile nodes in VANETs. Specially, data trust is evaluated based on the data sensed and collected from multiple vehicles; node trust is assessed in two dimensions, i.e., functional trust and recommendation trust, which indicate how likely a node can fulfill its functionality and how trustworthy the recommendations from a node for other nodes will be, respectively. The effectiveness and efficiency of the proposed ART scheme is validated through extensive experiments. The proposed trust management theme is applicable to a wide range of VANET applications to improve traffic safety, mobility, and environmental protection with enhanced trustworthiness.

In recent years, Android has become one of the most popular mobile operating systems because of numerous mobile applications (apps) it provides. However, the malicious Android applications (malware) downloaded from third-party markets have significantly threatened users' security and privacy, and most of them remain undetected due to the lack of efficient and accurate malware detection techniques. In this paper, we study a malware detection scheme for Android platform using an SVM-based approach, which integrates both risky permission combinations and vulnerable API calls and use them as features in the SVM algorithm. To validate the performance of the proposed approach, extensive experiments have been conducted, which show that the proposed malware detection scheme is able to identify malicious Android applications effectively and efficiently.

A large amount and different types of mobile applications (or apps) are being offered to end users via app markets. These apps normally generate network traffic, which will consumes users' mobile data plan and may even cause potential security issues. However, the amount and type of network traffic generated by a mobile app in the wild is still poorly understood due to the lack of a systematic measurement methodology. In this paper, we first measure and analyze network traffic cost of Android apps in the official Android markets. Based on the results, we find that the apps from different categories have different traffic costs. In particular, there is a remarkable difference among the apps with similar functionality in terms of network traffic cost. Then, we add metrics of traffic cost into our app recommendation algorithm, which differs from the conventional app recommendation approaches. Experimental results show that the proposed recommendation algorithm can effectively help mobile app users avoid various potential security and privacy risks brought by the unnecessary network traffic consumption.

Android has become one of the most popular mobile operating systems because of numerous applications (apps) it provides. However, Android malware downloaded from third-party markets threatens users' privacy, and most of them remain undetected because of the lack of efficient and accurate detecting techniques. Prior efforts on Android malware detection attempted to build precise classification models by manually choosing features, and few of them has used any feature selection algorithms to help pick typical features. In this paper, we present Feature Extraction and Selection Tool (Fest), a feature-based machine learning approach for malware detection. We first implement a feature extraction tool, AppExtractor, which is designed to extract features, such as permissions or APIs, according to the predefined rules. Then we propose a feature selection algorithm, FrequenSel. Unlike existing selection algorithms which pick features by calculating their importance, FrequenSel selects features by finding the difference their frequencies between malware and benign apps, because features which are frequently used in malware and rarely used in benign apps are more important to distinguish malware from benign apps. In experiments, we evaluate our approach with 7972 apps, and the results show that Fest gets nearly 98% accuracy and recall, with only 2% false alarms. Moreover, Fest only takes 6.5s to analyze an app on a common PC, which is very time-efficient for malware detection in Android markets.

Vehicular Ad-hoc Networks (VANETs) are known to be very susceptible to various malicious attacks. To detect and mitigate these malicious attacks, many security mechanisms have been studied for VANETs. In this paper, we propose a context aware security framework for VANETs that uses the Support Vector Machine (SVM) algorithm to automatically determine the boundary between malicious nodes and normal ones. Compared to the existing security solutions for VANETs, The proposed framework is more resilient to context changes that are common in VANETs, such as those due to malicious nodes altering their attack patterns over time or rapid changes in environmental factors, such as the motion speed and transmission range. We compare our framework to existing approaches and present evaluation results obtained from simulation studies.

In this paper, we study a SVM-based malware detection scheme for Android application, which integrates both risky permission combinations and vulnerable API calls and use them as features in the SVM algorithm. Preliminary experiments have validated the proposed malware detection scheme.

Abstract With the rapid growth in the popularity of Android smartphones, a large number of Android applications (or apps) have emerged in both official and alternative Android markets. It is important for network operators and security analysts to understand the network traffic generated by new Android apps for the purposes of network management, app traffic analysis, and malware detection. However, it is time‐consuming and tedious to manually install and run Android apps to generate network traffic. Moreover, existing synthetic network traffic generators are unable to generate network traffic that can accurately reflect the network behaviors of Android apps. In this paper, we propose and implement AndroGenerator, an automated Android network traffic generation system, to generate various types of network traffic that can be produced by Android apps. Our system reproduces the network traffic based on the traffic characteristics extracted from traffic traces captured by running a large number of Android applications from several popular Android markets, such as Google Play. The system first generates network traffic through automated execution of Android applications. Then, the system is also able to extract network characteristics from the captured traffic traces and store the extracted results into a database for benchmarking purposes. Finally, AndroGenerator reproduces Android app traffic based via simulating network characteristics of captured traffic traces. In the experiments, we evaluate our system with real‐world mobile traffic, and the experiment results show that AndroGenerator can reproduce Android app network traffic accurately. Copyright © 2015 John Wiley & Sons, Ltd.

Wireless body area networks (BAN) has recently emerged as an important enabling technology to support various telehealth applications. Because of its unique application domain, it is critical to ensure the trustworthy and reliable gathering of patient's physiological data. In this paper, a trust management scheme (BAN-Trust) is proposed that does not rely on any encryption technique, and it can be efficiently deployed on commercial off-the-shelf sensor devices. The effectiveness of the BAN-Trust scheme is validated through experiments.

In this paper, we propose a trustworthy data management framework for wireless networks in Cyber-Physical System (CPS), in which the trust values of both CPS data and the reporting devices are assessed. In addition, a set of policy rules are declared to accurately describe how we determine the trustworthiness of each reporting device based on the contextual factors. Experimental results on both simulation and on real CPS datasets show that the proposed framework can properly evaluate the trustworthiness of the reporting devices and data in CPS.

Mobile Ad-hoc Networks (MANETs) are extremely susceptible to various misbehaviors and a variety of trust management schemes have been proposed to detect and mitigate them. Most schemes rely on a set of pre-defined weights to determine how the extent of each misbehavior is used to evaluate the trustworthiness. However, due to the extremely dynamic nature of MANETs, it is not possible to determine a set of weights that are appropriate for all contexts. In this paper, an Automated Trust Management (ATM) system is described for MANETs that uses a support vector machine classifier to detect malicious MANET nodes. The ATM scheme is resilient to attempts by a malicious MANET node to hide its nature by varying its misbehavior patterns over time. The performance of the ATM scheme is evaluated via an extensive simulation study and compared with existing approaches.

Nodes in Mobile Ad hoc Networks (MANETs) are required to relay data packets to enable communication between other nodes that are not in radio range with each other. However, whether for selfish or malicious reasons, a node may fail to cooperate during the network operations or even attempt to disturb them, both of which have been recognized as misbehaviors. Various trust management schemes have been studied to assess the behaviors of nodes so as to detect and mitigate node misbehaviors inMANETs. Most of existing schemes model a node's trustworthiness along a single dimension, combining all of the available evidence to calculate a single, scalar trust metric. A single measure, however, may not be expressive enough to adequately describe a node's trustworthiness in many scenarios. In this paper, we describe a multi-dimensional framework to evaluate the trustworthiness of MANET node from multiple perspectives. Our scheme evaluates trustworthiness from three perspectives: collaboration trust, behavioral trust, and reference trust. Different types of observations are used to independently derive values for these three trust dimensions. We present simulation results that illustrate the effectiveness of the proposed scheme in several scenarios.

Mobile Ad-hoc NETworks (MANETs) are known to be vulnerable to a variety of attacks due to lack of central authority or fixed network infrastructure. Many security schemes have been proposed to identify misbehaving nodes. Most of these security schemes rely on either a predefined threshold, or a set of well-defined training data to build up the detection mechanism before effectively identifying the malicious peers. However, it is generally difficult to set appropriate thresholds, and collecting training datasets representative of an attack ahead of time is also problematic. We observe that the malicious peers generally demonstrate behavioral patterns different from all the other normal peers, and argue that outlier detection techniques can be used to detect malicious peers in ad hoc networks. A problem with this approach is combining evidence from potentially untrustworthy peers to detect the outliers. In this paper, an outlier detection algorithm is proposed that applies the Dempster-Shafer theory to combine observation results from multiple nodes because it can appropriately reflect uncertainty as well as unreliability of the observations. The simulation results show that the proposed scheme is highly resilient to attackers and it can converge stably to a common outlier view amongst distributed nodes with a limited communication overhead.

The age of technology has changed the way that surgeons are being trained. Traditional methodologies for training can include lecturing, shadowing, apprenticing, and developing skills within live clinical situations. Computerized tools which simulate surgical procedures and/or experiences can allow for "virtual" experiences to enhance the traditional training procedures that can dramatically improve upon the older methods. However, such systems do not to adapt to the training context. We describe a ubiquitous computing system that tracks low-level events in the surgical training room (e.g. student locations, lessons completed, learning tasks assigned, and performance metrics) and from these derive the training context. This can be used to create an adaptive training system.