Engineering Commons^™

Re-Parameterizing Adversarial Reprogramming In Low-Dimensional Subspace For Efficient Software Vulnerability Detection, Hootan Alavizadeh

Browse all Theses and Dissertations

Software vulnerabilities are a major cause of security breaches, making effective detection critical. Traditional learning-based methods require large datasets and significant computational resources, which are often impractical due to high annotation costs and data scarcity. To address this, we propose an innovative system, RearVul, which Re-parameterizes adversarial reprogramming in a low-dimensional subspace for software vulnerability detection. Unlike conventional approaches, RearVul repurposes a pre-trained classification model using adversarial reprogramming, enabling detection with minimal modifications. It learns a universal perturbation applied to program representations, preserving the original model’s feature extraction capabilities while adapting it to a new domain. Furthermore, we introduce a …

Subjective Readiness Forecasting Using Supervised Machine Learning And Wearable Device Data, Nathaniel Michael Weiland

Browse all Theses and Dissertations

Recent advances in wearable technology allow continuous monitoring of physiological and behavioral data, opening new opportunities for real-time assessments of readiness and well-being. However, creating predictive models that generalize across diverse users remains challenging, especially in high-stakes settings like the military, where preventable injuries, illnesses, and stress-related performance declines are frequent. This research assesses the feasibility of using supervised machine learning models trained on wearable device data to predict subjective readiness indicators—recovery, stress, injury, and illness. Data from over 10,000 users in the OHWS (Optimizing the Human Weapons System) program combined daily check ins with physiological metrics from Garmin, Polar, …

Isometric Centroid Encoder (Ice) And Synthetic Data Generation Approaches For Biological Datasets, Prathyusha Kanakamalla

Browse all Theses and Dissertations

This thesis addressed two main challenges in biological data analysis: structure-preserving dimensionality reduction and synthetic data generation for small sample datasets. I proposed the Isometric Centroid Encoder (ICE), a supervised dimensionality reduction method that preserves pairwise distances between class centroids during dimension reduction. Unlike existing methods like Centroid Encoder and Super Encoder, ICE explicitly maintains geometric relationships between biological classes, achieving nearly perfect structure preservation at C dimensions (where C equals the number of classes) with strong performance even in 2D and 3D spaces. Additionally, I compared three generative models (VAE, LSH-GAN, and scDiffusion) for synthetic data generation on small …

Leveraging Counterfactuals For Enhanced Natural Language Inference: A Multitask Knowledge Distillation Approach, Brian J. Davis

Browse all Theses and Dissertations

Natural-language inference (NLI) asks whether a hypothesis is entailed by, contradicts, or is neutral with respect to a premise. Modern transformers reach high raw accuracy on benchmarks such as SNLI, MNLI, and ANLI, yet they often rely on brittle lexical shortcuts and provide little insight into their decision process. This thesis shows that counterfactual-augmented knowledge distillation can simultaneously boost robustness and supply faithful, token-level explanations—without scaling model size. Four T5-v1_1 students (60M, 220M, 770M, 3B parameters) are trained under four curricula: (1) standard fine-tuning, (2) fine-tuning with free-text rationales, (3) multi-task distillation with naive counterfactuals, and (4) multi-task distillation with …

Reinforcement Learning For Adversarial Systems Using Relational Observations, Sophia Christine Gilson

Browse all Theses and Dissertations

This thesis investigates the integration of relational observations with the reinforcement learning (RL) framework for improved generalization capability. A hide-and-seek simulation environment is designed in Unity for proof-of-concept demonstration. Two observation representations—relational (analogical) and standard positional—are designed to evaluate agent learning and generalization capabilities. Agents are trained using the Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC) algorithms in a random-room environment and tested in both the random-room environment and a novel environment with greater spatial complexity and path obstructions. Comparative studies indicate that relational representation of objects in the adversarial environment could potentially improve the generalization capability of …

Patient Subset Classification Using Encoded Embeddings And Knowledge Graph Retrieval-Augmented Generation, Benjamin A. Holmes

Browse all Theses and Dissertations

The widespread adoption of electronic medical records has created a vast reservoir of clinical data that can be leveraged to better understand how interventions relate to patient outcomes. Much of this information, however, exists as unstructured free-text, posing significant challenges for traditional statistical and machine-learning methods. Solving these challenges would allow the extraction of specific patient subpopulations (clinically relevant cohorts of individuals who share overlapping symptoms, risk factors, or diagnostic criteria), which could be used in precision medicine. Despite this promise, extracting these subpopulations from unstructured medical notes is an ongoing challenge due to the variability of clinical language and …

Generative Adversarial Networks (Gans) For High-Dimensional Biological Data, Harigovind Harikumar

Browse all Theses and Dissertations

This thesis investigates the application of Generative AI models, mainly Generative Adversarial Network (GAN) models to high dimensional and low sample size biological datasets like Motion Sickness, Breast Cancer, Crohn, and Melanoma. We utilized and compared three generative AI frameworks: Vanilla GAN, Wasserstein GAN (WGAN), Locality-Sensitive Hashing GAN (LSH-GAN) and Omics GAN. To address the challenges associated with high-dimensionality and low sample size, which was leading to very poor outputs of biological synthetic samples, we came up with an approach to stop the model when it reaches its saturation level. That is, we printed the loss plots to see where …

Learning Under Data Scarcity: Reasoning And Negative Distillation For Texts And Graphs, Calvin T. Greenewald

Browse all Theses and Dissertations

Modern machine learning (ML) models rely on large amounts of high-quality labeled data to achieve optimal performance. However, in many real-world domains, such as cyber security, acquiring sufficient labeled data is often infeasible due to cost, privacy concerns, and the rapid evolution of underlying phenomena. This challenge underscores the importance of learning under data scarcity. This thesis addresses this challenge by proposing distinct, modality-specific techniques for text and graph domains, which allow models to generalize effectively with minimal data. For text classification task, we incorporate distilled rationales from large language models and adversarial perturbations into the input space to improve …

Measuring And Improving Api Usability And Quality: A Comprehensive Framework And Empirical Study, Sultan Alanazy

Computer Science and Engineering Theses and Dissertations

Cloud computing provides on-demand access to flexible computing resources, enabling rapid application deployment without substantial infrastructure investment. Application Programming Interfaces (APIs) play an important role in ensuring the success of cloud applications. The primary users of APIs are the extensive community of application programmers who search, read, and understand APIs before integrating them into their applications or systems. In addition, developers often turn to online API support when seeking help. Problems in such support can result in incorrect API usage and integration problems. There is an urgent need to measure API usability and support issues to identify, characterize, and assess …

Graph Neural Networks Powered Scientific Paper Recommendation, Junhao Shen

Computer Science and Engineering Theses and Dissertations

Scientific paper recommendation systems aim to help researchers discover relevant papers amidst the vast and ever-growing body of literature. With the exponential yearly increase in scientific publications, the demand for effective paper recommendation solutions has become both critical and increasingly challenging. In recent years, deep learning techniques have revolutionized recommender systems, and scientific paper recommendations have naturally integrated these advancements. In this dissertation, we address these challenges through three progressive contributions.

First, we enhance traditional content-based methods using Graph Neural Networks (GNNs) by introducing a Graph Convolutional Network-strengthened Topic Modeling (GCN-TM) approach. This method improves upon conventional topic modeling techniques …

Automated Solutions For Hydroponic Plant Growth, Sydney Mcclure, Adam Lachguar

Sustainability Conference

Within the past year, Project H.O.M.E. has been focusing on the design and development of a semi-automatic hydroponic system specifically for sustaining plant life in Martian-like conditions. Given the significance of extended space-based travel, where the duration of human life in space is a crucial factor, growing food becomes imperative. This project has integrated electrical engineering and computer science, with features like automated pH testing and sensor-based evaluations. Key functionalities, including timed watering and automatic adjustments, were coded to enhance plant care. Initially, the project’s comprehensive research and strategic planning resulted in detailed blueprints and computer-aided design models for the …

Synthetic Network Creation And Visualization, Kaylee Sloat, Jeremy Evert

Student Research

The code in the repository, “synthetic_network_creation_and_visualization” is inspired by the foundational work presented in "NetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks" by Shashank Pandit, Duen Horng Chau, Samuel Wang, and Christos Faloutsos.

Link to the original paper:https://kilthub.cmu.edu...

Inexact Methods For Large-Scale Stochastic Programming, Niloofar Fadavi

Operations Research and Engineering Management Theses and Dissertations

This dissertation addresses the development of inexact methods for solving large-scale stochastic programming problems, with a focus on two-stage and multistage settings. Stochastic programming is a robust approach for managing uncertainty in decision-making, with applications across various domains like supply chain management, power systems, and logistics. However, solving large-scale stochastic programming problems, especially those with a nonlinear structure, is computationally challenging due to the high-dimensional nature of uncertainties and the need for efficient optimization techniques.

This work introduces novel inexact proximal bundle algorithms designed to solve two-stage stochastic quadratic programming problems. The proposed methods utilize dual-based and partition-based approaches to …

Exploring The Potential Of Neutrosophic Topological Spaces In Computer Science, A. A. Salama, Huda E. Khalid, Ahmed K. Essa, Ahmed G. Mabrouk

Neutrosophic Systems with Applications

Neutrosophic topological spaces (NTS) offer a novel framework for uncertainty modeling by incorporating degrees of truth, indeterminacy, and falsity. This paper investigates the potential applications of NTS in computer science. We provide background on neutrosophic sets and their extension to topological spaces. We then explore how NTS could be used for uncertainty modeling in data analysis (e.g., handling noisy data in sensor networks), pattern recognition (e.g., improving image classification with imprecise features), and information retrieval (e.g., enhancing search results by considering relevance uncertainty). We discuss the challenges associated with applying NTS and highlight promising areas for future research, such as …

Exploring The Potential Of Neutrosophic Topological Spaces In Computer Science, A. A. Salama, Huda E. Khalid, Ahmed K. Essa, Ahmed G. Mabrouk

Neutrosophic Systems with Applications

Neutrosophic topological spaces (NTS) offer a novel framework for uncertainty modeling by incorporating degrees of truth, indeterminacy, and falsity. This paper investigates the potential applications of NTS in computer science. We provide background on neutrosophic sets and their extension to topological spaces. We then explore how NTS could be used for uncertainty modeling in data analysis (e.g., handling noisy data in sensor networks), pattern recognition (e.g., improving image classification with imprecise features), and information retrieval (e.g., enhancing search results by considering relevance uncertainty). We discuss the challenges associated with applying NTS and highlight promising areas for future research, such as …

Real Time Pii Scanning, John David

Electronic Theses and Dissertations

The increased amount of web applications and internet software solutions utilizing cloud frameworks has contributed to large data sets of system log messages being generated constantly. These messages may contain sensitive data, creating an additional security risk for the systems and contributing to the need for analysis of such large volumes of data in real time. Large commercial data monitoring systems can solve for these analysis requirements, but they can be costly. We present a solution to analyzing web application log data which ingests it, processes it and visualizes sensitive data found within in real time. Our solution utilizes an …

Heterogeneous Multi-Robot Person-Following In Constrained Environments, Ori A. Miller

Electronic Theses and Dissertations

Maintaining visibility of a person requires effective systems. Security cameras or ground robots might be ideal, but they often fail in uncontrolled or unknown environments. A single ground robot struggles to navigate and track an agent at the same time. This work addresses the challenge by developing a multi-robot system with a slow ground robot and an agile aerial robot. Three methods are evaluated: FORWARD-PF, RL-Person Following (RL), and a baseline closed-loop method. FORWARD-PF proved the most reliable, completing all nine paths and reaching targets nearly twice as fast as RL. Despite completing seven paths, RL faltered on complex tasks. …

Integrating Authentication Schemes In Augmented And Virtual Reality Classrooms, Naheem Noah

Electronic Theses and Dissertations

Augmented Reality and Virtual Reality (AR/VR) technologies are revolutionizing educational experiences, but their widespread adoption hinges on addressing critical security and usability challenges, particularly in the domain of user authentication. This research presents an investigation into the security landscape of AR/VR and explores a graphical authentication scheme called “Things” that enhances both security and usability in immersive learning environments. Through a systematic evaluation of popular AR/VR devices and applications, potential vulnerabilities and limitations were identified, such as high usage of pin/passwords which are susceptible to shoulder-surfing attacks, lack of multi-factor authentication, and unclear data-sharing practices. A review of existing knowledge-based …

Activity Map Generation And Event-Based Sensor Processing With Spiking Autoencoders And Sparse Dictionary Learning, Jack Easton

Computer Science and Engineering Theses and Dissertations

This thesis explores the potential of Spiking Neural Networks (SNNs) in processing event sensor data and generating high-fidelity activity maps. Event sensors capture asynchronous binary events with high dynamic range, but traditional processing methods often fail to leverage their advantages fully. SNNs, with their asynchronous, event-driven nature, offer a promising alternative.

A Spiking Autoencoder (SAE) was employed in this thesis to handle the stochastic and sparse event data, integrating deep dictionary learning to enhance the feature space and improve activity map quality. The encoder, modeled after the VGG network, extracts features from event streams generated by speckle patterns, which are …

Pinn-Chk: Physics-Informed Neural Network For High-Fidelity Prediction Of Early-Age Cement Hydration Kinetics, Md Asif Rahman, Tianjie Zhang, Yang Lu

Civil Engineering Faculty Publications and Presentations

Cement hydration kinetics, characterized by heat generation in early-age concrete, poses a modeling challenge. This work proposes a physics-informed neural network (PINN) named PINN-CHK designed for cement hydration kinetics, to predict early-age temperature rises in cement paste. PINN-CHK leverages data-driven solutions to craft a high-fidelity prediction model, encompassing material properties and maturity functions in cement hydration. Trained on heated cement paste data, it simultaneously fits experimental results and underlying physics, yielding a mesh-free simulation. Incorporating governing partial differential equations (PDEs), and initial and boundary conditions into its loss function, PINN-CHK architecture undergoes rigorous benchmark testing, demonstrating unparalleled predictive accuracy compared …

Improving Expressive Capacity Of Deep Neural Networks, Clayton Harper

Computer Science and Engineering Theses and Dissertations

Deep learning has had remarkable success in a variety of fields. However, architectures often rely on hyperparameter searches and heuristics for improved model performance. Performing hyperparameter searches is an arduous task--often time-consuming and potentially expensive to run on accelerated hardware. As a result, practitioners often rely on heuristics which may lead to sub-optimal results. In the context of deep learning, hyperparameters are set by the user prior to the training process and remain fixed. Deep learning uses gradient descent to learn complex feature representations from data, limiting human intervention. While the weights of the architecture can learn directly through data …

Welcome To Cheney App, Timothy Nelson, Nolan Posey, Tanner Stephenson, Daniel Palmer, Matthew Matriciano

2024 Symposium

Welcome to Cheney is a non-profit organization committed to fostering communication, connection, and action within the city of Cheney. Their primary purpose is to provide timely and accurate information to the residents of Cheney. Welcome to Cheney has tried utilizing other forms of social media such as Facebook and Instagram to share information, but their presence is being overshadowed amidst the noise on those platforms. Therefore, the intention of this project is to develop a mobile app with the sole purpose of being a reliable means of sharing important information with the residents of Cheney.

The information being shared on …

Exploring Equity, Diversity, And Inclusion In Computer Science Undergraduate Curricula, Ouldooz Baghban Karimi, Giulia Toti, Fiona Mcneill, Alice Gao, Rutwa Engineer, Shanon Reckinger, Peggy Lindner, Jinyoung Hur, Rebecca Robinson, Anna Sollazzo, Richard Wicentowski

Engineering Management and Systems Engineering Faculty Research & Creative Works

One of the less explored approaches to foster equity, diversity, and inclusion (EDI) in Computer Science (CS) is through changes to the curriculum. Despite sporadic work on the adoption of Culturally Responsive Computing (CRC) and Universal Design for Learning (UDL), the inclusion of equity-minded courses, or modifications on specific elements of the curriculum such as introductory programming courses, there has never been a wide exploration or adoption of a successful equity-minded undergraduate CS curriculum. In this work, we explore undergraduate CS curricula, with a special focus on upper division, lower division, and service courses (courses offered to non-CS students). For …

Problem Solving / Javascript Programming, Sarah Zelikovitz, Orit D. Gruber

Open Educational Resources

This Lab Experiment focuses on JavaScript Programming. Upon completing the lab, you will be able to understand the following:

· The definition of Algorithmic Problem Solving.

· The role of JavaScript in web pages.

· The concept of Iteration in computer programming.

Bridging Design And Perception: Novel Tools And Technologies For Creating Effective Human-Robot Interactions, Benjamin Dossett

Electronic Theses and Dissertations

This thesis explores human perception of robots through the use of novel tools and technologies. First, the impact of Augmented Reality (AR) data presentation on human perception of robots is investigated. A study conducted with the AR human-robot teaming system found that robot performance significantly influenced participants’ perceptions, overshadowing the impact of matching or mismatching robot confidence feedback. Second, the DU Want to Build-A-Bot platform is presented, which enables participatory robot design and opens the door for novel research of how robot design affects human perception. The Build-A-Bot platform enables the collection of diverse robot designs, facilitating machine learning analysis …

Beyond The Horizon: Exploring Anomaly Detection Potentials With Federated Learning And Hybrid Transformers In Spacecraft Telemetry, Juan Rodriguez

Computer Science and Engineering Theses and Dissertations

Telemetry sensors play a crucial role in spacecraft operations, providing essential data on efficiency, sustainability, and safety. However, identifying irregularities in telemetry data can be a time-consuming process that risks the success of missions. With the rise of CubeSats and smallsats, telemetry data has become more abundant, but concerns about privacy and scalability have resulted in untapped data potential. To address these issues, we propose a new approach to anomaly detection that utilizes machine learning models at data sources. These models solely transmit weights to a centralized server for aggregation, resulting in improved dataset performance with a single global model. …

Intelligent Resource Allocation For Sdn/Nfv-Enabled Networks Through Reinforcement Learning, Jing Su

Computer Science and Engineering Theses and Dissertations

Software-Defined Networking (SDN) and Network Functions Virtualization (NFV) are two emerging paradigms that enable the feasible and scalable deployment of Virtual Network Functions (VNFs) in commercial-off-the-shelf (COTS) devices, which deliver a range of network services with reduced cost. The deployment of these services requires efficient resource allocation that fulfills the requirements in terms of Quality of Service (QoS) and Service-Level Agreement (SLA) while considering the constraints of the underlying infrastructure, such as maximum latency tolerance and affinity policies.

An optimized resource allocation result can benefit the network in various aspects, such as energy-saving, performance boost, and latency reduction. To achieve …

Neuro-Symbolic Commonsense Reasoning With Resistance To Data Poisoning: A First-Order Logic And Sub-Symbolic Embeddings Framework, Bryce Shurts, King-Ip Lin

Computer Science and Engineering Theses and Dissertations

Commonsense reasoning has long presented a hurdle between conversational agents and their ability to naturally engage with humans in conversation, as the infinitely dimensional nature of a dialogue’s topics presents a significant reasoning challenge in the study of Natural Language Understanding (NLU). Such a system must conceivably be able to act as a generalizable system for evaluating and reasoning about commonsense statements, problems, and queries: in this way, the agent can attempt to quantify the reasonability of a given input. We attempt to address this through the integration of an explainable neuro-symbolic system that leverages Logical Tensor Networks (LTNs) and …

Analyzing Information Cascades Through Machine Learning And Data Analytics, Betul Agirman

Honors Scholar Theses

In today's digital age, social media platforms have become pivotal in influencing public opinion and behavior, with information spreading being both beneficial and detrimental. This rapid spread is typically called an information cascade, and they are important in further understanding social influence, managing misinformation, and even predicting potential trends of public responses. With social media, people are connected so easily to one another like a network, wherein it becomes possible for them to influence each other’s behavior and decisions. Utilizing a dataset from Weibo that spans critical periods of the COVID-19 outbreak, this study integrates machine learning and data analytics …

Data Analysis Of Twitter’S Nasdaq100 Sentiments And Topics As Indicators For News Articles Retrieval: Fine-Tuning Roberta And Rag, Kagan Timur

ICT

This study explores the combination of sentiment analysis with vader-lexicon and semantic analysis with latent dirichlet allocation to identify real-life events, particularly in the context of Twitter datasets. While sentiment analysis alone may not provide accurate guidance, the inclusion of semantic analysis enhances the research process by helping to identify relevant news articles and comprehend brand perception on social media. Furthermore, the study fine-tunes the RoBERTa model specifically for question-answering tasks