OS and Networks Commons^™

Learning Network-Based Multi-Modal Mobile User Interface Embeddings, Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Rich multi-modal information - text, code, images, categorical and numerical data - co-exist in the user interface (UI) design of mobile applications. UI designs are composed of UI entities supporting different functions which together enable the application. To support effective search and recommendation applications over mobile UIs, we need to be able to learn UI representations that integrate latent semantics. In this paper, we propose a novel unsupervised model - Multi-modal Attention-based Attributed Network Embedding (MAAN) model. MAAN is designed to capture both multi-modal and structural network information. Based on the encoder-decoder framework, MAAN aims to learn UI representations that …

Practical Server-Side Wifi-Based Indoor Localization: Addressing Cardinality & Outlier Challenges For Improved Occupancy Estimation, Anuradha Ravi, Archan Misra

Research Collection School Of Computing and Information Systems

Server-side WiFi-based indoor localization offers a compelling approach for passive occupancy estimation (i.e., without requiring active participation by client devices, such as smartphones carried by visitors), but is known to suffer from median error of 6–8 meters. By analyzing the characteristics of an operationally-deployed, WiFi-based passive indoor location system, based on the classical RADAR algorithm, we identify and tackle 2 practical challenges for accurate individual device localization. The first challenge is the low-cardinality issue, whereby only the associated AP generates sufficiently frequent RSSI reports, causing a client to experience large localization error due to the absence of sufficient measurements from …

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples, Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu

Research Collection School Of Computing and Information Systems

The ability to read, reason, and infer lies at the heart of neural reasoning architectures. After all, the ability to perform logical reasoning over language remains a coveted goal of Artificial Intelligence. To this end, models such as the Turing-complete differentiable neural computer (DNC) boast of real logical reasoning capabilities, along with the ability to reason beyond simple surface-level matching. In this brief, we propose the first probe into DNC's logical reasoning capabilities with a focus on text-based question answering (QA). More concretely, we propose a conceptually simple but effective adversarial attack based on metamorphic relations. Our proposed adversarial attack …

Toward A Quantum Neural Network: Proposing The Qaoa Algorithm To Replace A Feed Forward Neural Network, Erick Serrano

Undergraduate Research Symposium Posters

With a surge in popularity of machine learning as a whole, many researchers have sought optimization methods to reduce the complexity of neural networks; however, only recent attempts have been made to optimize neural networks via quantum computing methods. In this paper, we describe the training process of a feed forward neural network (FFNN) and the time complexity of the training process. We highlight the inefficiencies of the FFNN training process, particularly when implemented with gradient descent, and introduce a call to action for optimization of a FFNN. Afterward, we discuss the strides made in quantum computing to improve the …

Optimizing Networking Topologies With Shortest Path Algorithms, Jordan Sahs

UNO Student Research and Creative Activity Fair

Communication networks tend to contain redundant devices and mediums of transmission, thus the need to locate, document, and optimize networks is increasingly becoming necessary. However, many people do not know where to start the optimization progress. What is network topology? What is this “Shortest Path Problem”, and how can it be used to better my network? These questions are presented, taught, and answered within this paper. To supplement the reader’s understanding there are thirty-eight figures in the paper that are used to help convey and compartmentalize the learning process needed to grasp the materials presented in the ending sections.

In …

Analysis Of System Performance Metrics Towards The Detection Of Cryptojacking In Iot Devices, Richard Matthews

Masters Theses & Doctoral Dissertations

This single-case mechanism study examined the effects of cryptojacking on Internet of Things (IoT) device performance metrics. Cryptojacking is a cyber-threat that involves stealing the computational resources of devices belonging to others to generate cryptocurrencies. The resources primarily include the processing cycles of devices and the additional electricity needed to power this additional load. The literature surveyed showed that cryptojacking has been gaining in popularity and is now one of the top cyberthreats. Cryptocurrencies offer anyone more freedom and anonymity than dealing with traditional financial institutions which make them especially attractive to cybercriminals. Other reasons for the increasing popularity of …

Analyzing The Effectiveness Of Legal Regulations And Social Consequences For Securing Data, Howard B. Goodman

Masters Theses & Doctoral Dissertations

There is a wide range of concerns and challenges related to stored data security – which range from privacy and management to operations readiness, These challenges span from financial to personal and public impact. With an abundance of regulations for the enforcement of data security and emerging requirements proposed every year, organizations cannot avoid the legal or social implications of inadequate data protection. Today, public spotlight and awareness are challenging organizations to enhance how data is protected more than at any other time. For this reason, organizations have made significant efforts to improve security.

When looking at precautions or changes, …

On-Device Deep Learning Inference For System-On-Chip (Soc) Architectures, Tom Springer, Elia Eiroa-Lledo, Elizabeth Stevens, Erik Linstead

Engineering Faculty Articles and Research

As machine learning becomes ubiquitous, the need to deploy models on real-time, embedded systems will become increasingly critical. This is especially true for deep learning solutions, whose large models pose interesting challenges for target architectures at the “edge” that are resource-constrained. The realization of machine learning, and deep learning, is being driven by the availability of specialized hardware, such as system-on-chip solutions, which provide some alleviation of constraints. Equally important, however, are the operating systems that run on this hardware, and specifically the ability to leverage commercial real-time operating systems which, unlike general purpose operating systems such as Linux, can …

Towards Identity Relationship Management For Internet Of Things, Mohammad Muntasir Nur

Masters Theses & Doctoral Dissertations

Identity and Access Management (IAM) is in the core of any information systems. Traditional IAM systems manage users, applications, and devices within organizational boundaries, and utilize static intelligence for authentication and access control. Identity federation has helped a lot to deal with boundary limitation, but still limited to static intelligence – users, applications and devices must be under known boundaries. However, today’s IAM requirements are much more complex. Boundaries between enterprise and consumer space, on premises and cloud, personal devices and organization owned devices, and home, work and public places are fading away. These challenges get more complicated for Internet …

Traversing Nat: A Problem, Tyler Flaagan

Masters Theses & Doctoral Dissertations

This quasi-experimental before-and-after study measured and analyzed the impacts of adding security to a new bi-directional Network Address Translation (NAT). Literature revolves around various types of NAT, their advantages and disadvantages, their security models, and networking technologies’ adoption. The study of the newly created secure bi-directional model of NAT showed statistically significant changes in the variables than another model using port forwarding. Future research of how data will traverse networks is crucial in an ever-changing world of technology.

Deep Learning For Anomaly Detection: Challenges, Methods, And Opportunities, Guansong Pang, Longbing Cao, Charu Aggarwal

Research Collection School Of Computing and Information Systems

In this tutorial we aim to present a comprehensive survey of the advances in deep learning techniques specifically designed for anomaly detection (deep anomaly detection for short). Deep learning has gained tremendous success in transforming many data mining and machine learning tasks, but popular deep learning techniques are inapplicable to anomaly detection due to some unique characteristics of anomalies, e.g., rarity, heterogeneity, boundless nature, and prohibitively high cost of collecting large-scale anomaly data. Through this tutorial, audiences would gain a systematic overview of this area, learn the key intuitions, objective functions, underlying assumptions, advantages and disadvantages of different categories of …

Deepis: Susceptibility Estimation On Social Networks, Wenwen Xia, Yuchen Li, Jun Wu, Shenghong Li

Research Collection School Of Computing and Information Systems

Influence diffusion estimation is a crucial problem in social network analysis. Most prior works mainly focus on predicting the total influence spread, i.e., the expected number of influenced nodes given an initial set of active nodes (aka. seeds). However, accurate estimation of susceptibility, i.e., the probability of being influenced for each individual, is more appealing and valuable in real-world applications. Previous methods generally adopt Monte Carlo simulation or heuristic rules to estimate the influence, resulting in high computational cost or unsatisfactory estimation error when these methods are used to estimate susceptibility. In this work, we propose to leverage graph neural …

Neural Architecture Search As Sparse Supernet, Y. Wu, A. Liu, Zhiwu Huang, S. Zhang, Gool L. Van

Research Collection School Of Computing and Information Systems

This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for …

Decision-Guided Weighted Automata Extraction From Recurrent Neural Networks, Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun

Research Collection School Of Computing and Information Systems

Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in learning and processing sequential data (e.g., speech and natural language). However, due to the black-box nature of neural networks, understanding the decision logic of RNNs is quite challenging. Some recent progress has been made to approximate the behavior of an RNN by weighted automata. They provide better interpretability, but still suffer from poor scalability. In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. In particular, we identify the patterns of RNN’s step-wise predictive decisions to instruct the …

Learning To Pre-Train Graph Neural Networks, Yuanfu Lu, Xunqiang Jiang, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) have become the de facto standard for representation learning on graphs, which derive effective node representations by recursively aggregating information from graph neighborhoods. While GNNs can be trained from scratch, pre-training GNNs to learn transferable knowledge for downstream tasks has recently been demonstrated to improve the state of the art. However, conventional GNN pre-training methods follow a two-step paradigm: 1) pre-training on abundant unlabeled data and 2) fine-tuning on downstream labeled data, between which there exists a significant gap due to the divergence of optimization objectives in the two steps. In this paper, we conduct an …

Treecaps: Tree-Based Capsule Networks For Source Code Processing, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). While graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code need static code semantic analysis that may not be accurate and introduces noise during learning. On the other hand, syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs. We propose a new tree-based learning technique, named TreeCaps, by fusing capsule networks with tree-based convolutional neural networks, to …

Scalable Verification Of Quantized Neural Networks, Thomas A. Henzinger, Mathias Lechner, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network’s correctness. Thus, …

The U-Net-Based Active Learning Framework For Enhancing Cancer Immunotherapy, Vishwanshi Joshi

Theses, Dissertations and Capstones

Breast cancer is the most common cancer in the world. According to the U.S. Breast Cancer Statistics, about 281,000 new cases of invasive breast cancer are expected to be diagnosed in 2021 (Smith et al., 2019). The death rate of breast cancer is higher than any other cancer type. Early detection and treatment of breast cancer have been challenging over the last few decades. Meanwhile, deep learning algorithms using Convolutional Neural Networks to segment images have achieved considerable success in recent years. These algorithms have continued to assist in exploring the quantitative measurement of cancer cells in the tumor microenvironment. …

Improved Secure And Low Computation Authentication Protocol For Wireless Body Area Network With Ecc And 2d Hash Chain, Soohyeon Choi

Electronic Theses and Dissertations

Since technologies have been developing rapidly, Wireless Body Area Network (WBAN) has emerged as a promising technique for healthcare systems. People can monitor patients’ body condition and collect data remotely and continuously by using WBAN with small and compact wearable sensors. These sensors can be located in, on, and around the patient’s body and measure the patient’s health condition. Afterwards sensor nodes send the data via short-range wireless communication techniques to an intermediate node. The WBANs deal with critical health data, therefore, secure communication within the WBAN is important. There are important criteria in designing a security protocol for a …

Image Source Identification Using Convolutional Neural Networks In Iot Environment, Yan Wang, Qindong Sun, Dongzhu Rong, Shancang Li, Li Da Xu

Information Technology & Decision Sciences Faculty Publications

Digital image forensics is a key branch of digital forensics that based on forensic analysis of image authenticity and image content. The advances in new techniques, such as smart devices, Internet of Things (IoT), artificial images, and social networks, make forensic image analysis play an increasing role in a wide range of criminal case investigation. This work focuses on image source identification by analysing both the fingerprints of digital devices and images in IoT environment. A new convolutional neural network (CNN) method is proposed to identify the source devices that token an image in social IoT environment. The experimental results …

Integrating The Bullet Physics Engine Into Minecraft, Ethan Johnson

Student Academic Conference

During the past fall semester, I started a programming project called Rayon which is designed to be a realistic physics engine implementation that runs alongside the videogame Minecraft. It is a library which Minecraft mod developers can use to implement realistic entity movement into their own mods. Rayon, being entirely written in the Java programming language, currently uses a port of the Bullet physics engine called JBullet which is very outdated and no longer being maintained. To find a more performant solution, I have set out to replace JBullet with an alternative library called LibBulletJME which is designed to interface …

Xtreme-Noc: Extreme Gradient Boosting Based Latency Model For Network-On-Chip Architectures, Ilma Sheriff

All Graduate Theses, Dissertations, and Other Capstone Projects

Multiprocessor System-on-Chip (MPSoC) integrating heterogeneous processing elements (CPU, GPU, Accelerators, memory, I/O modules ,etc.) are the de-facto design choice to meet the ever-increasing performance/Watt requirements from modern computing machines. Although at consumer level the number of processing elements (PE) are limited to 8-16, for high end servers, the number of PEs can scale up to hundreds. A Network-on-Chip (NoC) is a microscale network that facilitates the packetized communication among the PEs in such complex computational systems. Due to the heterogeneous integration of the cores, execution of diverse (serial and parallel) applications on the PEs, application mapping strategies, and many other …

Unsupervised Representation Learning By Predicting Random Distances, Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma

Research Collection School Of Computing and Information Systems

Deep neural networks have gained great success in a broad range of tasks due to its remarkable capability to learn semantically rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption in unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications to critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected …

On Studying Distributed Machine Learning, Simeon Eberz

Senior Honors Theses

The Internet of Things (IoT) is utilizing Deep Learning (DL) for applications such as voice or image recognition. Processing data for DL directly on IoT edge devices reduces latency and increases privacy. To overcome the resource constraints of IoT edge devices, the computation for DL inference is distributed between a cluster of several devices. This paper explores DL, IoT networks, and a novel framework for distributed processing of DL in IoT clusters. The aim is to facilitate and simplify deployment, testing, and study of a distributed DL system, even without physical devices. The contributions of this paper are a deployment …

Secure Network Access Via Ldap, Nicholas Valaitis

Williams Honors College, Honors Research Projects

Networks need the ability to be access by secure accounts and users. The goal of this project is to configure and expand on LDAP configurations with considerations for AAA via TACACS+ and Radius for network equipment. This will provide adequate security for any given network in terms of access and prevent lose of access to devices which happens all to often with locally configured accounts on devices.

Preforming A Vulnerability Assessment On A Secured Network, Mathias Sovine

Williams Honors College, Honors Research Projects

A computer network will be built using 3 routers, 1 switch, and 4 computers. The network will be used to simulate the connections between an at home office and the internet. The network will be divided into 3 sub-networks. The routers will be secured using methods like access control lists, changing default admin passwords, and network encryption. The switch will be secured using methods like switchport security and setting access passwords. Once the network is secured, three penetration testing techniques and three exploits will be performed on the network. The results of the exploits and penetration testing techniques will be …

Lightweight Encryption Based Security Package For Wireless Body Area Network, Sangwon Shin

Electronic Theses and Dissertations

As the demand of individual health monitoring rose, Wireless Body Area Networks (WBAN) are becoming highly distinctive within health applications. Nowadays, WBAN is much easier to access then what it used to be. However, due to WBAN’s limitation, properly sophisticated security protocols do not exist. As WBAN devices deal with sensitive data and could be used as a threat to the owner of the data or their family, securing individual devices is highly important. Despite the importance in securing data, existing WBAN security methods are focused on providing light weight security methods. This led to most security methods for WBAN …

Statistical Modeling Of Hpc Performance Variability And Communication, Jered B. Dominguez-Trujillo

Computer Science ETDs

Understanding the performance of parallel and distributed programs remains a focal point in determining how compute systems can be optimized to achieve exascale performance. Lightweight, statistical models allow developers to both characterize and predict performance trade-offs, especially as HPC systems become more heterogeneous with many-core CPUs and GPUs. This thesis presents a lightweight, statistical modeling approach of performance variation which leverages extreme value theory by focusing on the maximum length of distributed workload intervals. This approach was implemented in MPI and evaluated on several HPC systems and workloads. I then present a performance model of partitioned communication which also uses …

Efficient Algorithms For Identifying Loop Formation And Computing Θ Value For Solving Minimum Cost Flow Network Problems, Timothy Michael Chávez, Duc Thai Nguyen

Computational Modeling & Simulation Engineering Faculty Publications

While the minimum cost flow (MCF) problems have been well documented in many publications, due to its broad applications, little or no effort have been devoted to explaining the algorithms for identifying loop formation and computing the value needed to solve MCF network problems. This paper proposes efficient algorithms, and MATLAB computer implementation, for solving MCF problems. Several academic and real-life network problems have been solved to validate the proposed algorithms; the numerical results obtained by the developed MCF code have been compared and matched with the built-in MATLAB function Linprog() (Simplex algorithm) for further validation.

Technical Q8a Site Answer Recommendation Via Question Boosting, Zhipeng Gao, Xin Xia, David Lo, John Grundy

Research Collection School Of Computing and Information Systems

Software developers have heavily used online question and answer platforms to seek help to solve their technical problems. However, a major problem with these technical Q&A sites is "answer hungriness" i.e., a large number of questions remain unanswered or unresolved, and users have to wait for a long time or painstakingly go through the provided answers with various levels of quality. To alleviate this time-consuming problem, we propose a novel DeepAns neural network-based approach to identify the most relevant answer among a set of answer candidates. Our approach follows a three-stage process: question boosting, label establishment, and answer recommendation. Given …