Continuous Mobile User Authentication Using a Hybrid CNN-Bi-LSTM Approach

Internet of Things (IoT) devices incorporate a large amount of data in several fields, including those of medicine, business, and engineering. User authentication is paramount in the IoT era to assure connected devices’ security. However, traditional authentication methods and conventional biometrics-based authentication approaches such as face recognition, fingerprints, and password are vulnerable to various attacks, including smudge attacks, heat attacks, and shoulder surfing attacks. Behavioral biometrics is introduced by the powerful sensing capabilities of IoT devices such as smart wearables and smartphones, enabling continuous authentication. Artificial Intelligence (AI)-based approaches introduce a bright future in refining large amounts of homogeneous biometric data to provide innovative user authentication solutions. This paper presents a new continuous passive authentication approach capable of learning the signatures of IoT users utilizing smartphone sensors such as a gyroscope, magnetometer, and accelerometer to recognize users by their physical activities. This approach integrates the convolutional neural network (CNN) and recurrent neural network (RNN) models to learn signatures of human activities from different users. A series of experiments are conducted using the MotionSense dataset to validate the effectiveness of the proposed method. Our technique offers a competitive verification accuracy equal to 98.4%. We compared the proposed method with several conventional machine learning and CNN models and found that our proposed model achieves higher identification accuracy than the recently developed verification systems. The high accuracy achieved by the proposed method proves its effectiveness in recognizing IoT users passively through their physical activity patterns.     

Multi-Factor Password-Authenticated Key Exchange via Pythia PRF Service

Multi-factor authentication (MFA) was proposed by Pointcheval et al. [Pointcheval and Zimmer (2008)] to improve the security of single-factor (and two-factor) authentication. As the backbone of multi-factor authentication, biometric data are widely observed. Especially, how to keep the privacy of biometric at the password database without impairing efficiency is still an open question. Using the vulnerability of encryption (or hash) algorithms, the attacker can still launch offline brute-force attacks on encrypted (or hashed) biometric data. To address the potential risk of biometric disclosure at the password database, in this paper, we propose a novel efficient and secure MFA key exchange (later denoted as MFAKE) protocol leveraging the Pythia PRF service and password-to-random (or PTR) protocol. Armed with the PTR protocol, a master password pwd can be translated by the user into independent pseudorandom passwords (or rwd) for each user account with the help of device (e.g., smart phone). Meanwhile, using the Pythia PRF service, the password database can avoid leakage of the local user’s password and biometric data. This is the first paper to achieve the password and biometric harden service simultaneously using the PTR protocol and Pythia PRF.     

A process for supporting risk-aware web authentication mechanism choice

Web authentication is often treated as a one-size-fits-all problem with ubiquitous use of the password. Indeed, authentication is seldom tailored to the needs of either the site or the target users. This paper does an in-depth analysis of all the vulnerabilities of authentication mechanisms, and proposes a structured and simple process which, if followed, will enable developers to choose a web authentication mechanism so that it matches the needs of their particular site.     

Multi Sensor-Based Implicit User Identification

Smartphones have ubiquitously integrated into our home and work environments, however, users normally rely on explicit but inefficient identification processes in a controlled environment. Therefore, when a device is stolen, a thief can have access to the owner’s personal information and services against the stored passwords. As a result of this potential scenario, this work proposes an automatic legitimate user identification system based on gait biometrics extracted from user walking patterns captured by smartphone sensors. A set of preprocessing schemes are applied to calibrate noisy and invalid samples and augment the gait-induced time and frequency domain features, then further optimized using a non-linear unsupervised feature selection method. The selected features create an underlying gait biometric representation able to discriminate among individuals and identify them uniquely. Different classifiers are adopted to achieve accurate legitimate user identification. Extensive experiments on a group of 16 individuals in an indoor environment show the effectiveness of the proposed solution: with 5 to 70 samples per window, KNN and bagging classifiers achieve 87–99% accuracy, 82–98% for ELM, and 81–94% for SVM. The proposed pipeline achieves a 100% true positive and 0% false-negative rate for almost all classifiers.     

Biometric verification with correlation filters

Using biometrics for subject verification can significantly improve security over that of approaches based on passwords and personal identification numbers, both of which people tend to lose or forget. In biometric verification the system tries to match an input biometric (such as a fingerprint, face image, or iris image) to a stored biometric template. Thus correlation filter techniques are attractive candidates for the matching precision needed in biometric verification. In particular, advanced correlation filters, such as synthetic discriminant function filters, can offer very good matching performance in the presence of variability in these biometric images (e.g., facial expressions, illumination changes, etc.). We investigate the performance of advanced correlation filters for face, fingerprint, and iris biometric verification.     

An Internet-enabled image- and model-based virtual machining system

Virtual reality (VR) can be described as a four-dimensional (4-D) simulation of the real world, including the 3-D geometry space, 1-D time and the immersive or semi-immersive interaction interface. VR applications in mechanical-related research areas are becoming popular, e.g. virtual layout design, virtual prototyping, Internet-based virtual manufacturing, etc. However, research in VR applications is facing conflicting requirements for high rendering quality and near real-time interactivity. This paper represents an Internet-based virtual machining system that builds an integrated VR scene, which combines images and models, to overcome the above conflicts. This research is divided into three parts: first, image mosaics techniques are used to implement an Internet-based virtual workshop, which is an image-based virtual scene. The method of obtaining original sequential images, the principle of image mosaics to realize automatic seamless stitching, and projection transformation matrices to reconstruct a closed inward-facing space are presented. Secondly, a model-based virtual milling machine has been constructed with three detailed approaches: a category-based dynamic graph structure to support collision detection, a relation-oriented collision detection method to improve the efficiency of collision detection, and a dynamic modelling method to model a dynamic workpiece object. Finally, an Internet-based virtual milling system, which is the integration of the image-based virtual workshop and the model-based virtual CNC machine, is constructed using the reposition method to achieve visual consistency of the virtual objects and images. This system, which includes an integrated scene, combines the advantages of image-based VR and model-based VR. Consequently, this system has both high rendering quality and good real-time interactivity.     

Novel AR-based interface for human-robot interaction and visualization

Intuitive and efficient interfaces for humanrobot interaction(HRI) have been a challenging issue in robotics as it is essential for the prevalence of robots supporting humans in key areas of activities.This paper presents a novel augmented reality(AR) based interface to facilitate human-virtual robot interaction.A number of human-virtual robot interaction methods have been formulated and implemented with respect to the various types of operations needed in different robotic applications.A EucUdean distance-based method is developed to assist the users in the interaction with the virtual robot and the spatial entities in an AR environment.A monitor-based visualization mode is adopted as it enables the users to perceive the virtual contents associated with different interaction methods,and the virtual content augmented in the real environment is informative and useful to the users during their interaction with the virtual robot.Case researches are presented to demonstrate the successful implementation of the AR-based HRI interface in planning robot pick-and-place operations and path following operations.     

Validation of virtual reality as a tool to understand and prevent child pedestrian injury

In recent years, virtual reality has emerged as an innovative tool for health-related education and training. Among the many benefits of virtual reality is the opportunity for novice users to engage unsupervised in a safe environment when the real environment might be dangerous. Virtual environments are only useful for health-related research, however, if behavior in the virtual world validly matches behavior in the real world. This study was designed to test the validity of an immersive, interactive virtual pedestrian environment. A sample of 102 children and 74 adults was recruited to complete simulated road-crossings in both the virtual environment and the identical real environment. In both the child and adult samples, construct validity was demonstrated via significant correlations between behavior in the virtual and real worlds. Results also indicate construct validity through developmental differences in behavior; convergent validity by showing correlations between parent-reported child temperament and behavior in the virtual world; internal reliability of various measures of pedestrian safety in the virtual world; and face validity, as measured by users' self-reported perception of realism in the virtual world. We discuss issues of generalizability to other virtual environments, and the implications for application of virtual reality to understanding and preventing pediatric pedestrian injuries.     

应用虚拟现实技术的人机交互仿真系统开发

针对现有虚拟仿真系统在人机交互、实时响应、数据采集等方面存在的不足,综合运用多种虚拟现实软、硬件技术构建出一个可供人与虚拟操作对象进行实时人机交互的仿真系统。利用数据转换技术将设计对象导入该系统后,系统能通过实时采集人机交互过程中的相关操作数据,测量人机交互绩效,继而评价设计质量。实例应用证明了系统的可行性。     

Keystroke dynamics enabled authentication and identification using triboelectric nanogenerator array

Cyber security has become a serious concern as the internet penetrates every corner of our life over the last two decades. The rapidly developing human–machine interfacing calls for an effective and continuous authentication solution. Herein, we developed a two-factor, pressure-enhanced keystroke-dynamics-based security system that is capable of authenticating and even identifying users through their unique typing behavior. The system consists of a rationally designed triboelectric keystroke device that converts typing motions into analog electrical signals, and a support vector machine (SVM) algorithm-based software platform for user classification. This unconventional keystroke device is self-powered, stretchable and water/dust proof, which makes it highly mobile and applicable to versatile working environments. The promising application of this novel system in the financial and computing industry can push cyber security to the next level, where leaked passwords would possibly be of no concern.     

Simulation-based scanning of a structured light system for objects without overhangs

This paper proposes an automated scanning process of a structured light system for objects without overhangs. The processes for scanning those objects need to plan scanning directions that minimise the missing area on a three-dimensional surface during the scanning process. Thus, the processes require an approach that finds the next scanning direction efficiently in terms of computational costs. This paper develops a scanning simulation approach to meet this requirement. In order to apply the developed approach, the proposed process generates a solution space for candidate-scanning directions, and represents an intermediate 3D model. The developed approach traverses the solution space in a virtual environment and executes virtual scanning for the intermediate 3D model. The virtual scanning result of each candidate-scanning direction is analysed in order to evaluate the contribution for filling missing area. The proposed process defines key scanning directions in the solution space through the iterative execution of the developed approach. The proposed process has been implemented, and applied to the scanning experiments of dental impressions.     

A virtual environment for training overhead crane operators: real-time implementation

In a manufacturing enterprise, virtual environments can improve productivity by allowing employees to train without taking production equipment out of service. As a demonstration of this capability, we have developed a virtual environment to simulate overhead crane operation. This virtual environment was developed by combining 3-D factory drawings with 3-D simulation models of crane and load motion. The crane simulator allows an operator to maneuver a crane and load in three dimensions. Implemented on a PC with an update rate of 14.3 Hz, the simulator runs in real-time interaction that approximates live machinery.     

Virtual figure model crafting with VR HMD and Leap Motion

Handcrafting has been used for purposes ranging from learning and entertainment to stress relief. However, clay art and handicrafts require specialized space and physical materials. In this paper, we propose a virtual figure model crafting system that is developed to allow users to directly experience the figure model crafting process using a head-mounted, display-based, virtual reality environment. In the proposed system, users can freely generate the shape of a figure and decorate its exterior. In order to provide realistic crafting user experiences, we leverage motion grammar-based gestural input with Leap Motion and consider the support of multiple difficulty levels for user engagement. The preliminary user study results confirm that the proposed system provides immersive and interactive crafting experiences in a virtual environment.     

面向自动测试系统的图形化编程平台的仪器接口模块的设计

面向自动测试系统的图形化编程平台的出现,为虚拟仪器系统集成工程师们提供了一个图形化的设计环境,可以极大地提高自动测试系统的集成率。     

Recognition of polychromatic three-dimensional objects

We propose to use optical multichannel correlation in various chromatic systems to obtain a setup for recognition of polychromatic three-dimensional (3-D) objects based on Fourier-transform profilometry. Because red-green-blue color components are not able to split the luminance information of objects in a defined component, when the 3-D objects are brighter than the reference objects the correlation result gives false alarms. We demonstrate that it is possible to use different color spaces that can split luminance from chromatic information to yield adequate recognition of polychromatic 3-D objects. We show experimental results that prove the utility of the proposed method.     

Secure authentication system that generates seed from biometric information

As biometric recognition techniques are gradually improved, the stability of biometric authentication systems are enhanced. Although bioinformation has properties that make it resistant to fraud, biometric authentication systems are not immune to hacking. We show a secure biometric authentication system (1) to guarantee the integrity of biometric information by mixing data by use of a biometric key and (2) to raise recognition rates by use of bimodal biometrics.     

Depth Transfer by an Imaging System

In many applications such as three-dimensional (3-D) data acquisition, the scanning of 3-D objects or 3-D display, it is necessary to understand how an imaging system can be used to obtain information on the structure of an object in the direction perpendicular to the image plane, i.e. depth information. In certain cases the formation of a 3-D image can be described by a theory based on optical transfer functions (OTF): the image intensity distribution is given by the 3-D convolution of the object and a 3-D point spread function (PSF); equivalently, in 3-D Fourier space the image spectrum is the product of the object spectrum and a 3-D OTF. This paper investigates the 3-D PSFs and OTFs that are associated with different pupil functions of the imaging system.     

A new virtual-instrumentation-based experimenting environment forundergraduate laboratories with application in research andmanufacturing

An undergraduate laboratory based on a functionally complete set of virtual tools for experimenting is described in this paper. An outstanding feature of the experimenting environment is an easy-to-use, graphical user interface to a laboratory experiment. It significantly shortens the time needed to implement experimenter-defined laboratory procedures and eliminates the need for high-level-language programming on the experimenter side. Taking advantage of industry-wide standards such as VISA, GPIB, and VXI, our virtual instruments can perform their function using either physical or simulated, local, or remote and network-distributed instruments coming from a variety of different manufacturers. A paperless laboratory with on-screen graded measurement reports was fully implemented. The environment allows remote experimenting-world-wide in principle. It currently requires a remote LabVIEW or XWindow session. Work is in progress on giving full access to our virtual tools using Java-capable web browsers such as Netscape, Hot Java, or Microsoft Internet Explorer and thus to provide students with a student-affordable remote experimenting platform     

A security enhanced mutual authentication scheme based on nonce and smart cards

There are many mutual authentication schemes proposed in the literature for preventing unauthorized parties from accessing resources in an insecure environment. However, most of them based on smart cards have assumed a tamper resistant condition for the smart card. To solve the problem, Huang, Liu, and Chen (2013) proposed a mutual authentication scheme based on nonce and smart cards and claimed that the adversary was not able to attack and access the system even if he could extract the data stored in the smart card. Unfortunately, in this paper, we will demonstrate that Huang et al.’s scheme is vulnerable to the offline password guessing attack and the privileged insider attack. We also propose an improved scheme to overcome the weaknesses.     

基于真实世界隐喻的虚拟现实用户界面范式研究及应用

目的 基于真实世界隐喻,研究虚拟现实用户界面范式,并指导应用实践。方法 通过整理虚拟现实和用户界面的相关文献资料,以基于真实世界的交互（RBI框架）作为指导,引出真实世界隐喻4个方面的要素,对比WIMP范式各个基础元件所承载的作用,研究虚拟现实用户界面范式。结论 提出了虚拟现实用户界面SOMM范式,分析了SOMM范式每一个要素,描述了用户在虚拟现实中的三维交互过程,并应用于工业机器人VR岗位实训系统用户界面当中,验证了SOMM范式的可行性。SOMM范式能让用户在虚拟现实环境中执行自然人机交互,减少了用户认知转换负荷,为其他研究者和设计师提供了指导和思路。