Computer Sciences Commons^™

Malware Classification Using Graph Neural Networks, Manasa Mananjaya

Master's Projects

Word embeddings are widely recognized as important in natural language pro- cessing for capturing semantic relationships between words. In this study, we conduct experiments to explore the effectiveness of word embedding techniques in classifying malware. Specifically, we evaluate the performance of Graph Neural Network (GNN) applied to knowledge graphs constructed from opcode sequences of malware files. In the first set of experiments, Graph Convolution Network (GCN) is applied to knowledge graphs built with different word embedding techniques such as Bag-of-words, TF-IDF, and Word2Vec. Our results indicate that Word2Vec produces the most effective word embeddings, serving as a baseline for comparison …

Concept Drift Detection In Android Malware, Inderpreet Singh

Master's Projects

Machine learning and deep learning algorithms have been successfully applied to the problems of malware detection, classification, and analysis. However, most of such studies have been limited to applying learning algorithms to a static snapshot of malware, which fails to account for concept drift, that is, the non-stationary nature of the data. In practice, models need to be updated whenever a sufficient level of concept drift has occurred. In this research, we consider concept drift detection in the context of Android malware. We train a series of Support Vector Machines (SVM) over sliding windows of time and compare the resulting …

Classifying World War Ii Era Ciphers With Machine Learning, Brooke Dalton

Master's Projects

We examine whether machine learning and deep learning techniques can classify World War II era ciphers when only ciphertext is provided. Among the ciphers considered are Enigma, M-209, Sigaba, Purple, and Typex. For our machine learning models, we test a variety of features including the raw ciphertext letter sequence, histograms, and n-grams. The classification is approached in two scenarios. The first scenario considers fixed plaintext encrypted with fixed keys and the second scenario considers random plaintext encrypted with fixed keys. The results show that histograms are the best feature and classic machine learning methods are more appropriate for this kind …

Keystroke Dynamics And User Identification, Atharva Sharma

Master's Projects

We consider the potential of keystroke dynamics for user identification and authentication. We work with a fixed-text dataset, and focus on clustering users based on the difficulty of distinguishing their typing characteristics. After obtaining a confusion matrix, we cluster users into different levels of classification difficulty based on their typing patterns. Our goal is to create meaningful clusters that enable us to apply appropriate authentication methods to specific user clusters, resulting in an optimized balance between security and efficiency. We use a novel feature engineering method that generates image-like features from keystrokes and employ multiclass Convolutional Neural Networks (CNNs) to …

Spam Comments Detection In Youtube Videos, Priyusha Kotta

Master's Projects

This paper suggests an innovative way for finding spam or ham comments on the video- sharing website YouTube. Comments that are contextually irrelevant for a particular video or have a commercial motive constitute as spam. In the past few years, with the advent of advertisements spreading to new arenas such as the social media has created a lucrative platform for many. Today, it is being widely used by everyone. But this innovation comes with its own impediments. We can see how malicious users have taken over these platforms with the aid of automated bots that can deploy a well-coordinated spam …

Federated Learning For Protecting Medical Data Privacy, Abhishek Reddy Punreddy

Master's Projects

Deep learning is one of the most advanced machine learning techniques, and its prominence has increased in recent years. Language processing, predictions in medical research and pattern recognition are few of the numerous fields in which it is widely utilized. Numerous modern medical applications benefit greatly from the implementation of machine learning (ML) models and the disruptive innovations in the entire modern health care system. It is extensively used for constructing accurate and robust statistical models from large volumes of medical data collected from a variety of sources in contemporary healthcare systems [1]. Due to privacy concerns that restrict access …

Machine Learning-Based Anomaly Detection In Cloud Virtual Machine Resource Usage, Tarun Mourya Satveli

Master's Projects

Anomaly detection is an important activity in cloud computing systems because it aids in the identification of odd behaviours or actions that may result in software glitch, security breaches, and performance difficulties. Detecting aberrant resource utilization trends in virtual machines is a typical application of anomaly detection in cloud computing (VMs). Currently, the most serious cyber threat is distributed denial-of-service attacks. The afflicted server's resources and internet traffic resources, such as bandwidth and buffer size, are slowed down by restricting the server's capacity to give resources to legitimate customers.

To recognize attacks and common occurrences, machine learning techniques such as …

Predictive Digital Twin For Optimizing Patient-Specific Radiotherapy Regimens Under Uncertainty In High-Grade Gliomas, Anirban Chaudhuri, Graham Pash, David A Hormuth, Guillermo Lorenzo, Michael Kapteyn, Chengyue Wu, Ernesto A B F Lima, Thomas E Yankeelov, Karen Willcox

Faculty, Staff and Student Publications

We develop a methodology to create data-driven predictive digital twins for optimal risk-aware clinical decision-making. We illustrate the methodology as an enabler for an anticipatory personalized treatment that accounts for uncertainties in the underlying tumor biology in high-grade gliomas, where heterogeneity in the response to standard-of-care (SOC) radiotherapy contributes to sub-optimal patient outcomes. The digital twin is initialized through prior distributions derived from population-level clinical data in the literature for a mechanistic model's parameters. Then the digital twin is personalized using Bayesian model calibration for assimilating patient-specific magnetic resonance imaging data. The calibrated digital twin is used to propose optimal …

Artificial Intelligence-Enabled Electrocardiographic Screening For Left Ventricular Systolic Dysfunction And Mortality Risk Prediction, Yu-Chang Huang, Yu-Chun Hsu, Zhi-Yong Liu, Ching-Heng Lin, Richard Tsai, Jung-Sheng Chen, Po-Cheng Chang, Hao-Tien Liu, Wen-Chen Lee, Hung-Ta Wo, Chung-Chuan Chou, Chun-Chieh Wang, Ming-Shien Wen, Chang-Fu Kuo

Faculty, Staff and Student Publications

BACKGROUND: Left ventricular systolic dysfunction (LVSD) characterized by a reduced left ventricular ejection fraction (LVEF) is associated with adverse patient outcomes. We aimed to build a deep neural network (DNN)-based model using standard 12-lead electrocardiogram (ECG) to screen for LVSD and stratify patient prognosis.

METHODS: This retrospective chart review study was conducted using data from consecutive adults who underwent ECG examinations at Chang Gung Memorial Hospital in Taiwan between October 2007 and December 2019. DNN models were developed to recognize LVSD, defined as LVEF

RESULTS: The mean age of patients in the testing dataset was 63.7 ± 16.3 years (46.3% …

Comparative Adjudication Of Noisy And Subjective Data Annotation Disagreements For Deep Learning, Scott David Williams

Browse all Theses and Dissertations

Obtaining accurate inferences from deep neural networks is difficult when models are trained on instances with conflicting labels. Algorithmic recognition of online hate speech illustrates this. No human annotator is perfectly reliable, so multiple annotators evaluate and label online posts in a corpus. Labeling scheme limitations, differences in annotators' beliefs, and limits to annotators' honesty and carefulness cause some labels to disagree. Consequently, decisive and accurate inferences become less likely. Some practical applications such as social research can tolerate some indecisiveness. However, an online platform using an indecisive classifier for automated content moderation could create more problems than it solves. …

Enhancing Graph Convolutional Network With Label Propagation And Residual For Malware Detection, Aravinda Sai Gundubogula

Browse all Theses and Dissertations

Malware detection is a critical task in ensuring the security of computer systems. Due to a surge in malware and the malware program sophistication, machine learning methods have been developed to perform such a task with great success. To further learn structural semantics, Graph Neural Networks abbreviated as GNNs have emerged as a recent practice for malware detection by modeling the relationships between various components of a program as a graph, which deliver promising detection performance improvement. However, this line of research attends to individual programs while overlooking program interactions; also, these GNNs tend to perform feature aggregation from neighbors …

Effective Systems For Insider Threat Detection, Muhanned Qasim Jabbar Alslaiman

Browse all Theses and Dissertations

Insider threats to information security have become a burden for organizations. Understanding insider activities leads to an effective improvement in identifying insider attacks and limits their threats. This dissertation presents three systems to detect insider threats effectively. The aim is to reduce the false negative rate (FNR), provide better dataset use, and reduce dimensionality and zero padding effects. The systems developed utilize deep learning techniques and are evaluated using the CERT 4.2 dataset. The dataset is analyzed and reformed so that each row represents a variable length sample of user activities. Two data representations are implemented to model extracted features …

Fuzzing Php Interpreters By Automatically Generating Samples, Jacob S. Baumgarte

Browse all Theses and Dissertations

Modern web development has grown increasingly reliant on scripting languages such as PHP. The complexities of an interpreted language means it is very difficult to account for every use case as unusual interactions can cause unintended side effects. Automatically generating test input to detect bugs or fuzzing, has proven to be an effective technique for JavaScript engines. By extending this concept to PHP, existing vulnerabilities that have since gone undetected can be brought to light. While PHP fuzzers exist, they are limited to testing a small quantity of test seeds per second. In this thesis, we propose a solution for …

Human Tracking Function For Robotic Dog, Andrew Sharkey

Williams Honors College, Honors Research Projects

With the increase the increase in automation and humans and robots working side by side, there is a need for a more organic way of controlling robots. The goal of this project is to create a control system for Boston dynamics robotic dog Spot that implements human tracking image software to follow humans using computer vision as well as using hand tracking image software to allow for control input through hand gestures.

Improving Developers' Understanding Of Regex Denial Of Service Tools Through Anti-Patterns And Fix Strategies, Sk Adnan Hassan, Zainab Aamir, Dongyoon Lee, James C. Davis, Francisco Servant

Department of Electrical and Computer Engineering Faculty Publications

Regular expressions are used for diverse purposes, including input validation and firewalls. Unfortunately, they can also lead to a security vulnerability called ReDoS (Regular Expression Denial of Service), caused by a super-linear worst-case execution time during regex matching. Due to the severity and prevalence of ReDoS, past work proposed automatic tools to detect and fix regexes. Although these tools were evaluated in automatic experiments, their usability has not yet been studied; usability has not been a focus of prior work. Our insight is that the usability of existing tools to detect and fix regexes will improve if we complement them …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyatt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis

Department of Electrical and Computer Engineering Faculty Publications

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Improving Lidar Fidelity For Hd Mapping Using Pattern Transplanting And Temporal Infill, Micah Bojrab

Wayne State University Dissertations

High Definition (HD) Mapping for Autonomous Driving creates an easily accessible wealth of information to confirm and enrich feedback from on-vehicle sensors. HD Maps built offline generally use dedicated ground collection vehicles equipped with high-cost, survey-grade LiDAR to accurately map a vehicle's areas of operation. We focus our work on controlled-access, divided highways characterized by wide roadways that require complex permutations to cover all directions of travel and access ramps. We study two common issues when collecting this road class that cause low-fidelity (LF) point clouds for HD Maps. First, aerial collection covers all directions and all ramps in a …

Predictable Dnn Inference For Autonomous Driving, Liangkai Liu

Wayne State University Dissertations

Deep neural networks (DNNs) are widely used in autonomous driving due to their high accuracy for perception, decision, and control. Predictability of the perception module is essential for the AV's safety. Predictability generally consists of two aspects: temporal and functional. Temporal aspects mean the task should be finished before the deadline. Functional aspects mean the task should make correct decisions. However, non-negligible time and performance variations are observed in DNN inference. Current DNN inference studies either ignore the variation issue or rely on the scheduler or the algorithm itself to handle it. None of the current work explains the roots …

Reproducibility In Management Science, David Moore, Miloš Fišar, Ben Greiner, Christoph Huber, Elena Katok, Ali I. Ozkes, Management Science Reproducibility Collaboration

Finance Faculty Works

With the help of more than 700 reviewers, we assess the reproducibility of nearly 500 articles published in the journal Management Science before and after the introduction of a new Data and Code Disclosure policy in 2019. When considering only articles for which data accessibility and hardware and software requirements were not an obstacle for reviewers, the results of more than 95% of articles under the new disclosure policy could be fully or largely computationally reproduced. However, for 29% of articles, at least part of the data set was not accessible to the reviewer. Considering all articles in our sample …

Detection And Localization Of Data Forgery Attacks In Automatic Generation Control, Fengli Zhang, Yatish R. Dubasi, Wei Bao, Qinghua Li

Electrical Engineering Faculty Publications and Presentations

Automatic Generation Control (AGC) is a key control system to maintain the power system’s balance between load and supply by maintaining its frequency in a specific range. It collects the tie-line power flow and frequency measurements of each control area to calculate the Area Control Error (ACE) and then adjusts power generation based on the calculated ACE. However, malicious frequency or tie-line power flow measurements can be injected and then AGC is misled to make false power generation adjustments which will harm power system operations. Such attacks can be carefully designed to pass the power system’s existing bad data detection …

Predicting Housing Prices Using Ai, Eric Sconyers

Williams Honors College, Honors Research Projects

I have created an AI model that can predict housing prices with 70 percent accuracy in Ames Iowa. I was able to use data from a website called Kaggle.com which is a website that provides datasets to the public so they can create AI models with the data. I found the dataset pertaining to housing prices in Ames Iowa. With this data, I was able to create an AI model that can predict the housing price of these homes. The technology I used in this project was Python as the programming language, and I used the scikit-learn library which has …

Exploration Of Digital Synthesis, Angelo Indre

Williams Honors College, Honors Research Projects

“An Exploration of Digital Synthesis” is a comprehensive investigation into the world of digital audio and music production. The paper explores the fundamental concepts of sound synthesis, including MIDI, virtual instruments (VSTs), and the JUCE framework. The central focus of the paper is the implementation of a custom synthesizer, which serves as a case study for the practical application of digital synthesis. The paper addresses the key question of how to create a functioning synthesizer from scratch, providing detailed insights into the programming and design process. Overall, the paper represents a significant contribution to the fields of digital audio and …

Liquid Tab, Nathan Hulet

Williams Honors College, Honors Research Projects

Guitar transcription is a complex task requiring significant time, skill, and musical knowledge to achieve accurate results. Since most music is recorded and processed digitally, it would seem like many tools to digitally analyze and transcribe the audio would be available. However, the problem of automatic transcription presents many more difficulties than are initially evident. There are multiple ways to play a guitar, many diverse styles of playing, and every guitar sounds different. These problems become even more difficult considering the varying qualities of recordings and levels of background noise.

Machine learning has proven itself to be a flexible tool …

The Future Between Quantum Computing And Cybersecurity, Daniel Dorazio

Williams Honors College, Honors Research Projects

Quantum computing, a novel branch of technology based on quantum theory, processes information in ways beyond the capabilities of classical computers. Traditional computers use binary digits [bits], but quantum computers use quantum binary digits [qubits] that can exist in multiple states simultaneously. Since developing the first two-qubit quantum computer in 1998, the quantum computing field has experienced rapid growth.

Cryptographic algorithms such as RSA and ECC, essential for internet security, rely on the difficulty of complex math problems that classical computers can’t solve. However, the advancement of quantum technology threatens these encryption systems. Algorithms, such as Shor’s, leverage the power …

Defense Of A Small Network, Isabella Adkins

Williams Honors College, Honors Research Projects

A sample network will be virtually created consisting of three routers, one switch, and three hosts. The network will be secured using various methods such as enabling passwords and encryption. After the network has been properly secured, various attacks will be attempted with the goal of breaking into the network. These attacks include reconnaissance (gathering information), penetrating the network using the tool Metasploit, and attempting to get a credential phishing email to end users. If successful in the attacks, the network will be revisited and analyzed for any weaknesses or oversights.

Discord Api Wrapper, Joshua Brown

Williams Honors College, Honors Research Projects

Discordwrap is a Python library that abstracts the Discord API so that developers can easily integrate their existing projects with Discord. This paper outlines Discordwrap's creation, from start to finish, including implementation as well as key design decisions, such as the decision to provide a functional library interface rather than an object-oriented one.

A Different Way To Penetrate Nba Defenses, Trey Trucksis

Williams Honors College, Honors Research Projects

This project proposal will document the design, configuration, and penetration testing of a network consisting of three routers (labeled as Lakers, Celtics, Cavaliers), one switch (labeled as NBA), and three end devices (labeled as Kali, Windows 10, and Ubuntu) each connected to one of three routers present on the network. Each router will be attached to a different subnet on the network. The network will be secured using encrypted passwords on the router interfaces, OSPF MD5 authentication between the routers, port security on the switch, as well as Access Control Lists to to control the privileges of each subnetwork accordingly. …

Small Business Office Network, Michael Gerome

Williams Honors College, Honors Research Projects

This project will emulate a small office network environment. The project will demonstrate the process of building and configuring the network to meet the requirements laid out in the project plan. This network includes four subnets with Windows 10 end devices and a Kali Linux device, it also includes five Cisco layer 2 switches and three Cisco routers. There are also three subnets connecting the routers to each other to enable routing between the subnets. After the network environment is set up, various penetration tests are performed from the Kali Linux device to gather information. The Nmap reconnaissance tool is …

Fridge Tracker And Recipe Provider : Fridgechamp, Matt Dudek

Williams Honors College, Honors Research Projects

FridgeChamp is a website to allow people to track their fridge/pantry contents while providing them recipes they can make with said ingredients. Currently there are few ingredient trackers and recipe matchers that exist as websites, and of those many lack simplistic recipes that a home chef would use. In addition to lacking some recipes, many tracker/recipe apps do not have a function to remove from your stock what a recipe requires, making you tediously update the stock every time you cook/use something.

Unsupervised-Based Distributed Machine Learning For Efficient Data Clustering And Prediction, Vishnu Vardhan Baligodugula

Browse all Theses and Dissertations

Machine learning techniques utilize training data samples to help understand, predict, classify, and make valuable decisions for different applications such as medicine, email filtering, speech recognition, agriculture, and computer vision, where it is challenging or unfeasible to produce traditional algorithms to accomplish the needed tasks. Unsupervised ML-based approaches have emerged for building groups of data samples known as data clusters for driving necessary decisions about these data samples and helping solve challenges in critical applications. Data clustering is used in multiple fields, including health, finance, social networks, education, and science. Sequential processing of clustering algorithms, like the K-Means, Minibatch K-Means, …