Search

Deep learning has been successfully utilized in many applications, but it is vulnerable to adversarial samples. To address this vulnerability, a generative adversarial network (GAN) has been used to train a robust classifier. This paper presents a novel GAN model and its implementation to defend against L∞ and L2 constraint gradient-based adversarial attacks. The proposed model is inspired by some of the related work, but it includes multiple new designs such as a dual generator architecture, four new generator input formulations, and two unique implementations with L∞ and L2 norm constraint vector outputs. The new formulations and parameter settings of GAN are proposed and evaluated to address the limitations of adversarial training and defensive GAN training strategies, such as gradient masking and training complexity. Furthermore, the training epoch parameter has been evaluated to determine its effect on the overall training results. The experimental results indicate that the optimal formulation of GAN adversarial training must utilize more gradient information from the target classifier. The results also demonstrate that GANs can overcome gradient masking and produce effective perturbation to augment the data. The model can defend PGD L2 128/255 norm perturbation with over 60% accuracy and PGD L∞ 8/255 norm perturbation with around 45% accuracy. The results have also revealed that robustness can be transferred between the constraints of the proposed model. In addition, a robustness–accuracy tradeoff was discovered, along with overfitting and the generalization capabilities of the generator and classifier. These limitations and ideas for future work will be discussed. [ABSTRACT FROM AUTHOR]

Model-checking and verification using Kripke structures and computational tree logic* (CTL*) use abstractions from the model/process/application to create the state-transition graphs that verify the model behavior. This scheme of profiling the performance of a process imports that the depth of the process operation correlates with the level abstraction. However, because of state explosion problems, these abstractions tend to restrict the scope to create manageable execution states. Therefore, for context modeling, this procedure does not generate a fine-grained behavioral model as generated states limit the ability of the abstraction to capture the execution time interactions amongst the processes, the hardware, and the kernel. Hence, in this paper, we present an end-to-end framework that comprises auto-encoders and probabilistic models to understand the behavior of system processes and detect deviant behaviors. We test this framework with a publicly available dataset generated from an autonomous aerial vehicle (UAV) application and the results show that by creating a fine-grained model that exploits previously unharnessed properties of the system calls, we can create a dynamic anomaly detection framework that evolves as the threats change. [ABSTRACT FROM AUTHOR]

Access to a variety of Internet of Things networks can be achieved through end-user devices such as smartphones or tablets. However, these devices are susceptible to theft, loss or unauthorized access. Although end-user devices are equipped with different means of authentication such as fingerprint readers, these methods are only employed at the time of access. Hence, an effective authentication mechanism that continuously authenticates users in the background is required in order to detect unauthorized access. A rich set of information can be extracted from end-user devices and utilized in the background to continuously authenticate users without requiring further intervention. As an example, the ability to continuously retrieve application usage profiles and sensor data on such devices strengthens the argument for employing behavioral-based mechanisms for continuous user authentication. This paper, which discusses behavioral-based authentication mechanisms with regard to security and usability, presents a user authentication model based on app access and network generated traffic patterns while accessing apps, utilizing a small amount of information. To validate our model, we use a public real-world dataset collected, in an uncontrolled manner, from real users over a long time period. The presented model can authenticate users with a minimum F-measure of 98%, utilizing both access time patterns and network traffic patterns. Overall, the results are promising, and the achieved high degree of accuracy proves the effectiveness and usability of the proposed model. [ABSTRACT FROM AUTHOR]

Smartphones have now become ubiquitous for accessing and controlling home appliances in smart homes, a popular application of the Internet of Things. User authentication on smartphones is mostly achieved at initial access. However, without applying a continuous authentication process, the network will be susceptible to unauthorized users. This issue emphasizes the importance of offering a continuous authentication scheme to identify the current user of the device. This can be achieved by extracting information during smartphone usage, including application access patterns. In this paper, we present a flexible machine learning user authentication scheme for smart home networks based on smartphone usage. Considering that users may run their smartphone applications differently during different day time intervals as well as different days of the week, new features are extracted by considering this information. The scheme is evaluated on a real-world dataset for continuous user authentication. The results show that the presented scheme authenticates users with high accuracy. [ABSTRACT FROM AUTHOR]

Modern applications, such as smart cities, home automation, and eHealth, demand a new approach to improve cloud application dependability and availability. Due to the enormous scope and diversity of the cloud environment, most cloud services, including hardware and software, have encountered failures. In this study, we first analyze and characterize the behaviour of failed and completed jobs using publicly accessible traces. We have designed and developed a failure prediction model to determine failed jobs before they occur. The proposed model aims to enhance resource consumption and cloud application efficiency. Based on three publicly available traces: the Google cluster, Mustang, and Trinity, we evaluate the proposed model. In addition, the traces were also subjected to various machine learning models to find the most accurate one. Our results indicate a significant correlation between unsuccessful tasks and requested resources. The evaluation results also revealed that our model has high precision, recall, and F1-score. Several solutions, such as predicting job failure, developing scheduling algorithms, changing priority policies, or limiting re-submission of tasks, can improve the reliability and availability of cloud services. [ABSTRACT FROM AUTHOR]

While several service discovery protocols and standards have been proposed for supporting service discovery from mobile devices, this remains a challenging problem. In many cases, mobile clients may discover services which they consider relevant but soon realize that such services are not completely usable on their mobile devices due to compatibility and interoperability issues. Without integrating device capabilities into the discovery process, or a device-aware mobile service discovery, it becomes extremely difficult to determine whether discovered services may or may not function properly within the device's constraints. This paper introduces a solution known as MobiEureka, a mobile device-aware system for enhancing the discovery of mobile web services from mobile devices. Experimental validation, results, and analysis of the introduced ideas are discussed. [ABSTRACT FROM AUTHOR]

This article discusses research into the measurement and improvement of Web based service identification on Internet search engines. Issues relating to the assessment of quality in the Web services identified through keyword searches are framed in terms of lack of transparency in the web service industry. The presentation of Web service applications and cloud computing systems on the Internet is described. The distinctions between user expectations when using Web Services and their approach to designing queries for other information storage and retrieval systems are noted.

Wireless mobile services are computing applications that run on handheld wireless devices. Such applications must work within the daunting constraints of the devices, which include memory, processing power, input capabilities, and size of display. It is therefore important that mobile services take into account the user’s context, optimize resource usage, and minimize input effort imposed on the user. In this paper, we present the design and implementation of a smart agent-enabled system for personalizing wireless mobile services and advertisements for Java 2 Micro Edition (J2ME) or Java ME, and Wireless Application Protocol (WAP) enabled devices. We use software agents for context filtering because such autonomous software entities have characteristics that can benefit mobile devices and the wireless environment, and the Composite Capability/Preference Profiles (CC/PP) standard for defining profiles for user preferences and device capabilities. The system incorporates the use of artificial neural networks to adaptively and iteratively learn to select the best available service based on contextual information. The system is evaluated using practical operating scenarios, as well as empirical data and results show an 87% success rate in the selection of the best available service. [ABSTRACT FROM AUTHOR]

Reliability estimation of mobile agent-based systems remains a difficult task due to the characteristics of mobile agents that include distributed and asynchronous execution, autonomy, and mobility. In this paper we present an analytical approach to estimate the reliability of mobile agent-based systems. We define the reliability of a mobile agent in terms of the processor execution time required to perform agent's tasks at each processing node and the transmission or communication time needed to transfer the agent from one processing node to another via a network to complete its mission. The failure of entire components causes failure of the agent. Simulation experiments have been conducted using stochastic Petri Nets modeling. We investigate the effect of different component reliability and availability models (processors and links) on the system throughput. The results we have obtained demonstrate the impact of different reliability and availability models on the system throughput. [ABSTRACT FROM AUTHOR]

The modularity of web services has left an open problem in composition, a scenario that involves an amalgamation of two or more web services to fulfill a request that no one web service is able to provide. This paper presents a framework for adaptive and dynamic composition of web services, enabling web services to be discovered either statically or dynamically by utilizing a semantic ontology to describe web services and their methods. This novel approach gives greater control on how web services are dynamically discovered by allowing the application developer to specify how matches are made, which goes beyond the present techniques of semantically matching inputs and outputs along with classification taxonomies. We utilize the Composite Capabilities/Preferences Profiles (CC/PP) to adapt the interface and content to be compatible with virtually any device. A proof of concept implementation has been constructed that enables users of any device to dynamically discover context-based services that will be dynamically composed to satisfy a user's request. In addition, we have designed and implemented a UDDI-like registry to support context-based adaptive composition of web services. Existing web services can be easily adapted and new web services can be effortlessly deployed. [ABSTRACT FROM AUTHOR]

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the threat of adversarial attacks. It is a training schema that utilizes an alternative objective function to provide model generalization for both adversarial data and clean data. In this systematic review, we focus particularly on adversarial training as a method of improving the defensive capacities and robustness of machine learning models. Specifically, we focus on adversarial sample accessibility through adversarial sample generation methods. The purpose of this systematic review is to survey state-of-the-art adversarial training and robust optimization methods to identify the research gaps within this field of applications. The literature search was conducted using Engineering Village (Engineering Village is an engineering literature search tool, which provides access to 14 engineering literature and patent databases), where we collected 238 related papers. The papers were filtered according to defined inclusion and exclusion criteria, and information was extracted from these papers according to a defined strategy. A total of 78 papers published between 2016 and 2021 were selected. Data were extracted and categorized using a defined strategy, and bar plots and comparison tables were used to show the data distribution. The findings of this review indicate that there are limitations to adversarial training methods and robust optimization. The most common problems are related to data generalization and overfitting. [ABSTRACT FROM AUTHOR]

A novel approach presented herein transforms the Human Machine Interface (HMI) states, as a pattern of visual feedback states that encompass both operator actions and process states, from a multi-variate time-series to a natural language processing (NLP) modeling domain. The goal of this approach is to predict operator response patterns for n − a h e a d time-step window given k − l a g g e d past HMI state patterns. The NLP approach offers the possibility of encoding (semantic) contextual relations within HMI state patterns. Towards which, a technique for framing raw HMI data for supervised training using sequence-to-sequence (seq2seq) deep-learning machine translation algorithms is presented. In addition, a custom Seq2Seq convolutional neural network (CNN) NLP model based on current state-of-the-art design elements such as attention, is compared against a standard recurrent neural network (RNN) based NLP model. Results demonstrate comparable effectiveness of both the designs of NLP models evaluated for modeling HMI states. RNN NLP models showed higher ( ≈ 26 % ) forecast accuracy, in general for both in-sample and out-of-sample test datasets. However, custom CNN NLP model showed higher ( ≈ 53 % ) validation accuracy indicative of less over-fitting with the same amount of available training data. The real-world application of the proposed NLP modeling of industrial HMIs, such as in power generating stations control rooms, aviation (cockpits), and so forth, is towards the realization of a non-intrusive operator situational awareness monitoring framework through prediction of HMI states. [ABSTRACT FROM AUTHOR]

The new University of Guelph-Humber has created in 2004 an innovative, combined university degree and college diploma program in computer science and communications technology. This venture between the university and the Humber Institute of Technology and Advanced Learning offers jointly an honors baccalaureate in computing science from Guelph and a diploma in wireless and telecommunications systems technology from Humber. The program, one of six joint programs between the two institutions, specializes in distributed and wireless computing. The program's details, faculty and staff and students were also described in the article.

Describes the Distributed Computing and Communications Systems Technology program offered by the University of Guelph-Humber. Courses; Focus of the courses on programming; Programming languages covered by the courses.

Localizing machine-type communication (MTC) devices or sensors is becoming important because of the increasing popularity of machine-to-machine (M2M) communication networks for location-based applications. These include such as health monitoring, rescue operations, vehicle tracking, and wildfire monitoring. Moreover, efficient localization approaches for sensor-based MTC devices reduce the localization error and energy consumption of MTC devices. Because sensors are used as an integral part of M2M communication networks and have achieved popularity in underwater applications, research is being conducted on sensor localization in both underwater and terrestrial M2M networks. Major challenges in designing underwater localization techniques are the lack of good radio signal propagation in underwater, sensor mobility management, and ensuring network coverage in 3D underwater M2M networks. Similarly, predicting the mobility pattern of MTC devices, trading-off energy consumption and location accuracy pose great design challenges for terrestrial localization techniques. This article presents a comprehensive survey on the current state-of-the-art research on both terrestrial and underwater localization approaches for sensor-based MTC devices. It also classifies localization approaches based on several factors, identifies their limitations with potential solutions, and compares them. Copyright © 2015 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

This article discusses the need to revitalize computer science education in the U.S. With the declining enrollments in computer science (CS) programs between 2002 and 2004, CS departments are encouraged to improve their offerings by reevaluating and redefining their programs and curriculum to match the needs of the information technology sector. Solutions are provided which focus on the specific CS courses a curriculum should contain. Equally important are how course materials should be delivered and how CS programs should be marketed.

Focuses on the development of a number of mobile agent platforms for handheld devices. Features of mobile agent platforms; Examples of web sites who are offering mobile agent platforms; Advantages of the MobiAgent system, a prototype agent-based framework and software infrastructure that minimizes the load on the wireless link and supports disconnected operations.

Making Web services context-aware is a challenge. This is like making Web service expose appropriate behaviors in response to changes detected in the environment. Context awareness requires a review and extension of the current execution model of Web services. This paper discusses the seamless combination of context and policy to manage behaviors that Web services expose during composition and in response to changes in the environment. For this purpose, a four-layer approach is devised. These layers are denoted by policy, user, Web service, and resource. In this approach, behavior management and binding are subject to executing policies of types permission, obligation, restriction, and dispensation. A prototype that illustrates how context and policy are woven into Web services composition scenarios is presented as well. [ABSTRACT FROM AUTHOR]