Engineering Commons^™

Evaluating The Resiliency Of Industrial Internet Of Things Process Control Using Protocol Agnostic Attacks, Hector L. Roldan

Theses and Dissertations

Improving and defending our nation's critical infrastructure has been a challenge for quite some time. A malfunctioning or stoppage of any one of these systems could result in hazardous conditions on its supporting populace leading to widespread damage, injury, and even death. The protection of such systems has been mandated by the Office of the President of the United States of America in Presidential Policy Directive Order 21. Current research now focuses on securing and improving the management and efficiency of Industrial Control Systems (ICS). IIoT promises a solution in enhancement of efficiency in ICS. However, the presence of IIoT …

Scatter Reduction By Exploiting Behaviour Of Convolutional Neural Networks In Frequency Domain, Carlos Ivan Jerez Gonzalez

Theses and Dissertations

In X-ray imaging, scattered radiation can produce a number of artifacts that greatly

undermine the image quality. There are hardware solutions, such as anti-scatter grids.

However, they are costly. A software-based solution is a better option because it is

cheaper and can achieve a higher scatter reduction. Most of the current software-based

approaches are model-based. The main issues with them are the lack of flexibility, expressivity, and the requirement of a model. In consideration of this, we decided to apply

Convolutional Neural Networks (CNNs), since they do not have any of the previously

mentioned issues.

In our approach we split …

Person Identification With Convolutional Neural Networks, Kang Zheng

Theses and Dissertations

Person identification aims at matching persons across images or videos captured by different cameras, without requiring the presence of persons’ faces. It is an important problem in computer vision community and has many important real-world applica- tions, such as person search, security surveillance, and no-checkout stores. However, this problem is very challenging due to various factors, such as illumination varia- tion, view changes, human pose deformation, and occlusion. Traditional approaches generally focus on hand-crafting features and/or learning distance metrics for match- ing to tackle these challenges. With Convolutional Neural Networks (CNNs), feature extraction and metric learning can be combined in …

Cybersecurity Issues In The Context Of Cryptographic Shuffling Algorithms And Concept Drift: Challenges And Solutions, Hatim Alsuwat

Theses and Dissertations

In this dissertation, we investigate and address two kinds of data integrity threats. We first study the limitations of secure cryptographic shuffling algorithms regarding preservation of data dependencies. We then study the limitations of machine learning models regarding concept drift detection. We propose solutions to address these threats.

Shuffling Algorithms have been used to protect the confidentiality of sensitive data. However, these algorithms may not preserve data dependencies, such as functional de- pendencies and data-driven associations. We present two solutions for addressing these shortcomings: (1) Functional dependencies preserving shuffle, and (2) Data-driven asso- ciations preserving shuffle. For preserving functional dependencies, …

Properties, Learning Algorithms, And Applications Of Chain Graphs And Bayesian Hypergraphs, Mohammad Ali Javidian

Theses and Dissertations

Probabilistic graphical models (PGMs) use graphs, either undirected, directed, or mixed, to represent possible dependencies among the variables of a multivariate probability distri- bution. PGMs, such as Bayesian networks and Markov networks, are now widely accepted as a powerful and mature framework for reasoning and decision making under uncertainty in knowledge-based systems. With the increase of their popularity, the range of graphical models being investigated and used has also expanded. Several types of graphs with dif- ferent conditional independence interpretations - also known as Markov properties - have been proposed and used in graphical models.

The graphical structure of a …

Stacked Modelling Framework, Kareem Abdelfatah

Theses and Dissertations

The thesis develops a predictive modeling framework based on stacked Gaussian processes and applies it to two main applications in environmental and chemical en- gineering. First, a network of independently trained Gaussian processes (StackedGP) is introduced to obtain analytical predictions of quantities of interest (model out- puts) with quantified uncertainties. StackedGP framework supports component- based modeling in different fields such as environmental and chemical science, en- hances predictions of quantities of interest through a cascade of intermediate predic- tions usually addressed by cokriging, and propagates uncertainties through emulated dynamical systems driven by uncertain forcing variables. By using analytical first and …

Challenges In Large-Scale Machine Learning Systems: Security And Correctness, Emad Alsuwat

Theses and Dissertations

In this research, we address the impact of data integrity on machine learning algorithms. We study how an adversary could corrupt Bayesian network structure learning algorithms by inserting contaminated data items. We investigate the resilience of two commonly used Bayesian network structure learning algorithms, namely the PC and LCD algorithms, against data poisoning attacks that aim to corrupt the learned Bayesian network model.

Data poisoning attacks are one of the most important emerging security threats against machine learning systems. These attacks aim to corrupt machine learning models by con- taminating datasets in the training phase. The lack of resilience of …

Model Augmented Deep Neural Networks For Medical Image Reconstruction Problems, Hongquan Zuo

Theses and Dissertations

Solving an ill-posed inverse problem is difficult because it doesn't have a unique solution. In practice, for some important inverse problems, the conventional methods, e.g. ordinary least squares and iterative methods, cannot provide a good estimate. For example, for single image super-resolution and CT reconstruction, the results of these conventional methods cannot satisfy the requirements of these applications. While having more computational resources and high-quality data, researchers try to use machine-learning-based methods, especially deep learning to solve these ill-posed problems. In this dissertation, a model augmented recursive neural network is proposed as a general inverse problem method to solve these …

Cybersecurity Education In Utah High Schools: An Analysis And Strategy For Teacher Adoption, Cariana June Cornel

Theses and Dissertations

The IT Education Specialist for the USBE, Brandon Jacobson, stated:I feel there is a deficiency of and therefore a need to teach Cybersecurity.Cybersecurity is the “activity or process, ability or capability, or state whereby information and communications systems and the information contained therein are protected from and/or defended against damage, unauthorized use or modification, or exploitation” (NICE, 2018). Practicing cybersecurity can increase awareness of cybersecurity issues, such as theft of sensitive information. Current efforts, including but not limited to, cybersecurity camps, competitions, college courses, and conferences, have been created to better prepare cyber citizens nationwide for such cybersecurity occurrences. In …

The Trust-Based Interactive Partially Observable Markov Decision Process, Richard S. Seymour

Theses and Dissertations

Cooperative agent and robot systems are designed so that each is working toward the same common good. The problem is that the software systems are extremely complex and can be subverted by an adversary to either break the system or potentially worse, create sneaky agents who are willing to cooperate when the stakes are low and take selfish, greedy actions when the rewards rise. This research focuses on the ability of a group of agents to reason about the trustworthiness of each other and make decisions about whether to cooperate. A trust-based interactive partially observable Markov decision process (TI-POMDP) is …

Machine Intelligence For Advanced Medical Data Analysis: Manifold Learning Approach, Fereshteh S Bashiri

Theses and Dissertations

In the current work, linear and non-linear manifold learning techniques, specifically Principle Component Analysis (PCA) and Laplacian Eigenmaps, are studied in detail. Their applications in medical image and shape analysis are investigated.

In the first contribution, a manifold learning-based multi-modal image registration technique is developed, which results in a unified intensity system through intensity transformation between the reference and sensed images. The transformation eliminates intensity variations in multi-modal medical scans and hence facilitates employing well-studied mono-modal registration techniques. The method can be used for registering multi-modal images with full and partial data.

Next, a manifold learning-based scale invariant global shape …

Cad-Based Porous Scaffold Design Of Intervertebral Discs In Tissue Engineering, Ye Guo

Theses and Dissertations

With the development and maturity of three-dimensional (3D) printing technology over the past decade, 3D printing has been widely investigated and applied in the field of tissue engineering to repair damaged tissues or organs, such as muscles, skin, and bones, Although a number of automated fabrication methods have been developed to create superior bio-scaffolds with specific surface properties and porosity, the major challenges still focus on how to fabricate 3D natural biodegradable scaffolds that have tailor properties such as intricate architecture, porosity, and interconnectivity in order to provide the needed structural integrity, strength, transport, and ideal microenvironment for cell- and …

Instantaneous Bandwidth Expansion Using Software Defined Radios, Nicholas D. Everett

Theses and Dissertations

The Stimulated Unintended Radiated Emissions (SURE) process has been proven capable of classifying a device (e.g. a loaded antenna) as either operational or defective. Currently, the SURE process utilizes a specialized noise radar which is bulky, expensive and not easily supported. With current technology advancements, Software Defined Radios (SDRs) have become more compact, more readily available and significantly cheaper. The research here examines whether multiple SDRs can be integrated to replace the current specialized ultra-wideband noise radar used with the SURE process. The research specifically targets whether or not multiple SDR sub-band collections can be combined to form a wider …

Confidence Inference In Defensive Cyber Operator Decision Making, Graig S. Ganitano

Theses and Dissertations

Cyber defense analysts face the challenge of validating machine generated alerts regarding network-based security threats. Operations tempo and systematic manpower issues have increased the importance of these individual analyst decisions, since they typically are not reviewed or changed. Analysts may not always be confident in their decisions. If confidence can be accurately assessed, then analyst decisions made under low confidence can be independently reviewed and analysts can be offered decision assistance or additional training. This work investigates the utility of using neurophysiological and behavioral correlates of decision confidence to train machine learning models to infer confidence in analyst decisions. Electroencephalography …

Cyber-Attack Drone Payload Development And Geolocation Via Directional Antennae, Clint M. Bramlette

Theses and Dissertations

The increasing capabilities of commercial drones have led to blossoming drone usage in private sector industries ranging from agriculture to mining to cinema. Commercial drones have made amazing improvements in flight time, flight distance, and payload weight. These same features also offer a unique and unprecedented commodity for wireless hackers -- the ability to gain ‘physical’ proximity to a target without personally having to be anywhere near it. This capability is called Remote Physical Proximity (RPP). By their nature, wireless devices are largely susceptible to sniffing and injection attacks, but only if the attacker can interact with the device via …

Near Real-Time Rf-Dna Fingerprinting For Zigbee Devices Using Software Defined Radios, Frankie A. Cruz

Theses and Dissertations

Low-Rate Wireless Personal Area Network(s) (LR-WPAN) usage has increased as more consumers embrace Internet of Things (IoT) devices. ZigBee Physical Layer (PHY) is based on the Institute of Electrical and Electronics Engineers (IEEE) 802.15.4 specification designed to provide a low-cost, low-power, and low-complexity solution for Wireless Sensor Network(s) (WSN). The standard’s extended battery life and reliability makes ZigBee WSN a popular choice for home automation, transportation, traffic management, Industrial Control Systems (ICS), and cyber-physical systems. As robust and versatile as the standard is, ZigBee remains vulnerable to a myriad of common network attacks. Previous research involving Radio Frequency-Distinct Native Attribute …

Unguided Cyber Education Techniques Of The Non-Expert, Seth A. Martin

Theses and Dissertations

The United States Air Force and Department of Defense continues to rely on its total workforce to provide the first layer of protection against cyber intrusion. Prior research has shown that the workforce is not adequately educated to perform this task. As a result, DoD cybersecurity strategy now includes attempting to improve education and training on cyber-related concepts and technical skills to all users of DoD networks. This paper describes an experiment designed to understand the broad methods that non-expert users may use to educate themselves on how to perform technical tasks. Preliminary results informed subsequent experiments that directly compared …

A Blockchain-Based Anomalous Detection System For Internet Of Things Devices, Joshua K. Mosby

Theses and Dissertations

Internet of Things devices are highly susceptible to attack, and owners often fail to realize they have been compromised. This thesis describes an anomalous-based intrusion detection system that operates directly on Internet of Things devices utilizing a custom-built Blockchain. In this approach, an agent on each node compares the node's behavior to that of its peers, generating an alert if they are behaving differently. An experiment is conducted to determine the effectiveness at detecting malware. Three different code samples simulating common malware are deployed against a testbed of 12 Raspberry Pi devices. Increasing numbers are infected until two-thirds of the …

Two-On-One Pursuit With A Non-Zero Capture Radius, Patrick J. Wasz

Theses and Dissertations

In this paper, we revisit the "Two Cutters and Fugitive Ship" differential game that was addressed by Isaacs, but move away from point capture. We consider a two-on-one pursuit-evasion differential game with simple motion and pursuers endowed with circular capture sets of radius l > 0. The regions in the state space where only one pursuer effects the capture and the region in the state space where both pursuers cooperatively and isochronously capture the evader are characterized, thus solving the Game of Kind. Concerning the Game of Degree, the algorithm for the synthesis of the optimal state feedback strategies of the …

Performance Analysis Of Angle Of Arrival Algorithms Applied To Radiofrequency Interference Direction Finding, Taylor S. Barber

Theses and Dissertations

Radiofrequency (RF) interference threatens the functionality of systems that increasingly underpin the daily function of modern society. In recent years there have been multiple incidents of intentional RF spectrum denial using terrestrial interference sources. Because RF based systems are used in safety-of-life applications in both military and civilian contexts, there is need for systems that can quickly locate these interference sources. In order to meet this need, the Air Force Research Laboratory Weapons Directorate is sponsoring the following research to support systems that will be able to quickly geolocate RF interferers using passive angle-of-arrival estimation to triangulate interference sources. This …

Preserving Privacy In Automotive Tire Pressure Monitoring Systems, Kenneth L. Hacker

Theses and Dissertations

The automotive industry is moving towards a more connected ecosystem, with connectivity achieved through multiple wireless systems. However, in the pursuit of these technological advances and to quickly satisfy requirements imposed on manufacturers, the security of these systems is often an afterthought. It has been shown that systems in a standard new automobile that one would not expect to be vulnerable can be exploited for a variety of harmful effects. This thesis considers a seemingly benign, but government mandated, safety feature of modern vehicles; the Tire Pressure Monitoring System (TPMS). Typical implementations have no security-oriented features, leaking data that can …

Optical Fiber Communication With Vortex Modes, Du'a Al-Zaleq

Theses and Dissertations

Internet data traffic’s capacity is rapidly reaching limits imposed by optical fiber nonlinearities [5]. Optical vortices appear in high order fiber optical mode. In this thesis, we consider multimode fibers (MMFs) that are capable of transmitting a few vortex modes. Certain types of fibers have a spatial dimension leads to space-division-multiplexing (SDM), where information is transmitted with cores of multicore fibers (MCFs) or mode-division-multiplexing (MDM), where information is transmitted via different modes of multimode fibers (MMFs). SDM by employing few-mode fibers in optical networks is expected to efficiently enhance the capacity and overcome the capacity crunch owing to fast increasing …