Computer Sciences Commons^™

Sequential Robustness In Adversarial Reinforcement Learning, Roman Lok-Ming Belaire

Dissertations and Theses Collection (Open Access)

My goal is to build autonomous systems that expand the reach of human capability in challenging domains such as undersea and space exploration, disaster response, and large-scale infrastructure. In everyday settings, these systems will increasingly appear in safety-critical applications such as autonomous driving, robotics, and industrial manufacturing. A central requirement for these systems is the ability to operate reliably under uncertainty, particularly when the environment behaves in unanticipated ways.

The robust handling of unforeseen environment dynamics is therefore a technical cornerstone of autonomous decision-making; Adversarial attacks provide a useful and principled lens through which to study this problem. Adversarial \textit{robustness}, …

Perspectives On Interpretability For Neural Text Representations, Jia Peng Lim

Dissertations and Theses Collection (Open Access)

In this dissertation, we investigate interpretability in the three elements of learning neural text representations: inputs, passed into models, to produce probabilistic outputs. We emphasise perspectives as we present alternative novel methods to mine and organise meaning in this work.

Models. We initiate our investigation by examining Neural Topic Models (NTM), proposing an alternate angle of interpreting its word-topic distribution, producing better topic representations for interpretation. Our method maps the problem of finding these better interpretations to classical NP-hard graph problems, enabling examination of topic distributions in a composite manner. Next, we apply our previous findings to extract interpretations from …

Sql Query Optimization - Human Vs. Chatgpt, Hailey Dennis

All Graduate Reports and Creative Projects, Fall 2023 to Present

Large Language Models (LLMs) such as ChatGPT have become ubiquitous tools for working professionals in the software industry. Many engineers are finding new ways to increase productivity by offloading tasks onto LLMs, while others are finding it difficult to trust code produced artificially, even after review. Taking a look at both perspectives, this study aims to compare a human’s ability to optimize SQL queries to that of an LLM and assess the experience using both methods.

Manual query optimization is a tedious task that relies heavily on statistics, heuristics, and good intuition. The SQL developer must search for the optimal …

Discovering Strategic Behaviors In The Floor Using Reinforcement Learning, Kevin Parks

All Graduate Reports and Creative Projects, Fall 2023 to Present

This project investigates how a reinforcement learning (RL) agent can develop territorial strategies in a highly stochastic, grid-based approximation of the television game show The Floor. I design a custom Gymnasium-compatible environment that models the show’s core mechanics on a 10×10 board, including probabilistic duels governed by player skill, adjacency-constrained attacks, chain-attack rules, and a Randomizer mechanism for selecting new initiating players. A Maskable Proximal Policy Optimization (Maskable PPO) agent is trained under several reward configurations and evaluated against stochastic non learning opponents as well as random and “always pass” baselines.

Across experiments, the best-performing configuration achieves a win …

Pyspqr: A Python Package For Density Estimation Using Deep Learning, Cameron Eddy, Reetam Majumder

Electrical Engineering and Computer Science Undergraduate Honors Theses

Splines are used for representing complex functions. In statistics, splines can be used for distributional shapes that are difficult to model by traditional parametric approaches. Ramsay (1) uses M-Spline bases to estimate continuous distributions. Semi-Parametric Quantile Regression (SPQR), developed by Xu and Reich (2), models conditional distributions where a neural network is used to estimate the basis function weights that depend on covariates. (3) implements a package for SPQR in R. We build on this by implementing a version of SPQR in Python with PyTorch. By using PyTorch, we can use more sophisticated deep learning architectures than those available in …

Towards Multi-Hop Retrieval Using Bipartite Question-Oriented Graphs, Micah Mccollum

Electrical Engineering and Computer Science Undergraduate Honors Theses

Accurately answering multi-hop questions requires full retrieval of multiple, interdependent passages and is a long-standing problem in the area of natural language question answering (QA). While retrieval-augmented generation (RAG) helps address single-hop questions, many retrievers presently focus on semantic similarity in a dense vector space, which is insufficient for handling multi-hop questions specifically. To ameliorate this, we propose constructing a bipartite question- oriented graph composed of hypothetically generated questions connected to passages at index time. The construction of the graph is guided by a large language model (LLM) to prioritize the formation of edges that signal whether a question can …

Evaluating The Use Of Extended Reality Technology To Improve Marching Band Conducting Patterns, Nathan R. Fuhrman

Electrical Engineering and Computer Science Undergraduate Honors Theses

Conducting pattern consistency is an essential skill for marching band drum

majors, yet developing this consistency through individual practice remains diffi-

cult without real-time feedback. This thesis investigates if the use of extended

reality technologies can be used to enhance the conducting skills of novice drum

majors. Using the Meta Quest 3’s passthrough capability, the system overlays vi-

sual feedback elements — including a 3D pattern guide, path visualization, tempo

cues, and a real-time score — onto the user’s physical environment. A within-

subjects study with seven participants evaluated eight combinations of three binary

feedback variables: pattern guide visibility, tempo …

​Autonomous Agentic Orchestration For Physics-Aware Scientific Discovery: An Integrative Multimodal Framework For 2d Material Characterization​, Sankalp Pandey

Electrical Engineering and Computer Science Undergraduate Honors Theses

The advancement of next-generation semiconductor and quantum technologies relies on the scalability of the fabrication of two-dimensional (2D) van der Waals heterostructures. However, this process is severely bottlenecked by characterization workflows. Optical microscopy provides high-throughput imaging of 2D material flakes, but lacks the explicit physical priors required for the discernment of sub-nanometer thickness variations, such as distinguishing monolayers from bilayers. The use of computer vision models to automate the localization and characterization process of the flakes was proposed. As a part of this effort, we develop QuantumFlake, an open-source framework to streamline the integration and deployment of computer vision models …

Datapeer: A Hybrid Interaction Model Web Application Integrating Llms For Human–Llm Collaboration In Data Analysis And Exploration, William I. Bumcum

Honors Theses

DataPeer is a web application that combines open-ended high agency (OHA) and structured low-agency (SLA) interaction paradigms to support human-LLM collaboration in exploratory data analysis. DataPeer integrates a large language model (LLM) with a React frontend and FastAPI backend, allowing both qualitative and quantitative analysis of user-uploaded CSV datasets through a chat-based interface. Users can attach datasets and provide natural language queries, while the LLM provides data analysis to the user. This thesis investigates the integration of LLMs into data analysis workflows and addresses gaps in interaction design and user agency in LLM-driven data tools by offering a responsive interface …

Analyzing The Writing Style Of Generative Ai When Prompted With Writing Samples, Samuel Mcdowell

Senior Honors Theses

Authorship attribution is an important topic in today’s world of Large Language Models (LLMs). It is the technology that helps to verify the author of a written work. This study explores whether LLMs can successfully mimic an individual’s writing style if they are given a text sample. A dataset of human-written texts was collected and used to prompt several LLMs to generate new texts that attempt to replicate the original author’s stylistic characteristics. The generated texts were then tested with modern authorship attribution models to determine whether they would be identified as being written by the original author. The results …

Volume 17, Christian O’Neill, Kyara Greene, Savva Sidorov, Laura Bisaillon, Luke Clemmer, Hannah Gordon, Kitt Benson, Taylor Blount, Rachel Danzitz, Nicholas Duellman, Chase Gionis, Hima Fernando, Seth Franzyshen, Onyx Gonzalez, Bryan Lin, Samantha Start, Ysabel Wells, Maggie Duncan

Incite: The Journal of Undergraduate Scholarship

Introduction Dr. Amorette Barber, Director, Office of Student Research

From the Editor Dr. Hannah Dudley-Shotwell

Cover Artist’s Statement Maggie Duncan

On Mentoring Dr. Yulia Uryadova

Ukrainian Resistance in the Face of Russification: Nestor Makhno and Anarchism

by Christian O’Neill

Life Vest by Kyara Greene

Isolation and 16S rRNA Identification of Bacteria from Fire Department Connection Pipe by Savva Sidorov

The Effectiveness of Planned Exercise in Reducing ADHD Symptoms in Children by Laura Bisaillon & Luke Clemmer

Linguistic Analysis on Confidence and Communication Strategies with Disparities Between Sign Fluency and Hearing Impairment by Hannah Gordon

Freedmen in Indian Territory by Kitt …

Analyzing The Evolution Of Science: Topological Cycles And Community Detection In Knowledge Networks, Frances C. Mcconnell

Mathematics, Statistics, and Computer Science Honors Projects

How scientific knowledge grows and organizes itself is a central question in the study of science. This thesis uses tools from topology and network science to detect and characterize knowledge gaps—places in a field’s literature where related concepts do not co-occur. We develop a metric to quantify the degree of interdisciplinarity of each gap, using the community structure of the underlying network as a proxy for subfields. Across a wide range of fields, gaps reliably span multiple subfields and evolve in recognizable temporal patterns, highlighting new insights into how scientific fields are structured and their stage of development.

Processing Conditions In Narrative Interpretation: A Structural Account Of Cf/Ef Divergence In "The Clerk's Tale”, Griselda Poe

Publications and Research

This paper applies the framework established in Paper 19, "Cognition Is Not Content: A Structural Account of Processing Conditions," to re-describe Chaucer's "The Clerk's Tale" from The Canterbury Tales.

The same narrative produces two incompatible interpretations: a record of domestic violence, and a story of genuine love. This divergence does not arise from differences in ethical judgment or emotional response. It arises from structural differences in the conditions under which information is reconstructed.

This paper does three things. First, it analyzes the characters Walter and Griselda in terms of CF (Core-foregrounded) and EF (Modulation-foregrounded) processing conditions. Second, it describes …

Friend Or Foe? The Benefits And Risks Of Llms In Cybersecurity, Niklas P. Dobler

Honors Theses

The rapid growth of Large Language Models (LLMs) and their continuous increase in capabilities have affected many professions and people. Due to advancements in areas such as coding and data analysis, they are now also being utilized in Cybersecurity. Recent research has examined their use in many different areas such vulnerability detection in code and analyzing network traffic. With this rapid growth, most organizations around the world are eager to advance faster than their competition, with limited considerations for the potential harm and risks these tools could bring. Some research has been conducted on malicious uses, but as the benefits …

Search For Slow-Moving Magnetic Monopoles With An Improved High-Energy Event Removal Algorithm, Reeshi N. Gihosal

Honors Theses

Fermilab’s NOvA (NuMI Off-axis 𝑣𝑒 Appearance) experiment focuses on understanding the behavior of neutrinos and how they affect the cosmos. A sub-focus of the NOvA experiment is the search for magnetic monopoles. These elusive particles have not yet been observed in nature, leaving their behavior to be mysterious. The Far Detector, located in Ash River, MN, is integral in the search for these particles. This project is on simulated magnetic monopoles with speeds thousandths the speed of light, with focus on the role of slicing algorithms in event reconstruction using the NOvA experiment’s reconstruction algorithm. Using sample data, analysis occurred …

Visualizing Probabilistic Model Checking: An Interactive Framework For Exploring Ctmc Models, Ishara Mawelle Kankanamge

All Graduate Theses and Dissertations, Fall 2023 to Present

Probabilistic model checking is a critical method for analyzing systems characterized by uncertainty, such as communication protocols, randomized algorithms, and biochemical networks. While formal verification tools provide precise numerical data about these systems, interpreting these results is often limited by large state space, high-dimensional state space and time dependent evolution. Current tools typically output raw numerical data, offering limited support for intuitively understanding the time-dependent behavior of a model. This research presents an interactive visualization framework designed to bridge the gap between complex numerical analysis and human intuition. The framework integrates coordinated visual interfaces, including lower-dimensional state-space projections and synchronized …

Quantitative Bounds On Resource Usage Of Probabilistic Programs, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Cost analysis, also known as resource usage analysis, is the task of finding bounds on the total cost of a program and is a well-studied problem in static analysis. In this work, we consider two classical quantitative problems in cost analysis for probabilistic programs. The first problem is to find a bound on the expected total cost of the program. This is a natural measure for the resource usage of the program and can also be directly applied to average-case runtime analysis. The second problem asks for a tail bound, i.e. ‍given a threshold t the goal is to find …

Market Reactions To Deceptive Language In Fake News: Implications From Language Expectancy Theory And Transfer Learning, Ka Chung Ng, Ping Fan Ke, Ping Fan, Mike So, Tam, Kar Yan

Research Collection School Of Computing and Information Systems

The advent of generative artificial intelligence (AI) has heightened the proliferation of fake news. A key challenge is the limited real-world data to investigate the societal impact of fake news produced by generative AI. In this paper, we examine stock market reactions to financial news articles that exhibit stylometric similarity to human-crafted and AI-crafted fake financial news. Grounded in language expectancy theory, we employ a style-based transfer learning model, pre-trained to recognizing deceptive language employed in various types of fake news intricacies. We then apply this model to a comprehensive dataset of financial news, assigning a “veracity style score” to …

Open Source Software Development Tool Installation: Challenges And Strategies For Novice Developers, Larissa Salerno, Christoph Treude, Patanamon Thongtanunam

Research Collection School Of Computing and Information Systems

As the world of technology advances, so do the tools that software developers use to create new programs. In recent years, software development tools have become more popular, allowing developers to work more efficiently and produce higher-quality software. Still, installing such tools can be challenging for novice developers at the early stage of their careers, as they may face issues such as compatibility problems (e.g., with operating systems) and unclear instructions. Therefore, this work aims to investigate the challenges novice developers face when installing software development tools and the strategies they employ to overcome them. To investigate these, we conducted …

Natural Adversaries: Fuzzing Autonomous Vehicles With Realistic Roadside Object Placements, Yang Sun, Haoyu Wang, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e., ensuring that they are not susceptible to critical misjudgements. It is important that these systems are tested not only with respect to other vehicles on the road, but also with respect to objects placed on the roadside. Trash bins, billboards, and greenery are examples of such objects, typically positioned according to guidelines developed for the human visual system, which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes or patches, which …

Fighting Against Recruitment Scams: Theory-Driven Supervised Learning And Empirical Analysis For Digital Fraudulent Recruitment Posting Behavior, Tom (Tianteng) Wang, David (Jingjun) Xu, Keng Siau, Zhongju (John) Zhang

Research Collection School Of Computing and Information Systems

The number of recruitment postings on digital recruitment hiring platforms has increased since the COVID-19 pandemic. However, the weak surveillance and operations of these platforms, combined with the fact that most job seekers have relatively low vigilance and a strong desire for recruitment offers, enable scammers to easily deceive job seekers for their money and confidential information. In this work, we combine prevailing text mining techniques (i.e., ChatGPT with prompting engineering and supervised machine learning) with interpersonal deception theory (IDT) from social science to design an interpretable IT system to predict fraudulent recruitment postings on digital recruitment-hiring platforms. We compare …

Enhancing Action And Ingredient Modeling For Semantically Grounded Recipe Generation, Guoshan Liu, Bin Zhu, Yian Li, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset and ingredient corpus, while RFT employs frequency-aware rewards to improve long-tail action prediction and ingredient generalization. A Semantic Confidence Scoring and Rectification (SCSR) module further filters and …

Leveraging Code Embeddings To Identify And Address Blind Spots In Benchmark Creation, Charles Moloney

School of Computing: Dissertations, Theses, and Student Research

Formal software verification remains critical for early vulnerability detection, yet benchmarking these tools is costly and often reliant on centralized datasets such as SV-COMP. While such repositories enable standardized evaluation, they introduce risks of overfitting and bias, particularly due to first-party benchmark contributions. To address these limitations, we extend ARG-V, our tool for generating SV-COMP-compatible benchmarks from real-world Java code, with a novel approach of using code embedding techniques to selectively sample from mined code. By leveraging Nomic Embed Code and a cosine-based Minimum Hyperspherical Energy (MHE) objective, we systematically select and transform benchmarks from scraped GitHub code that …

Benchmarking Gaslighting Attacks Against Speech Large Language Models, Jinyang Wu, Bin Zhu, Xiandong Zou, Qiquan Zhang

PhD Student’s Publications Collection

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial attacks in text-based LLMs and vision-language models, the unique cognitive and perceptual challenges of speech-based interaction remain underexplored. In contrast, speech presents inherent ambiguity, continuity, and perceptual diversity, which make adversarial attacks more difficult to detect. In this paper, we introduce gaslighting attacks, strategically crafted prompts designed to mislead, override, or distort model reasoning as a means to evaluate the vulnerability of Speech LLMs. Specifically, we construct five manipulation strategies: Anger, …

Teacher-Student Diffusion Model For Text-Driven 3d Hand Motion Generation, Ching Lam Cheng, Bin Zhu, Shengfeng He

PhD Student’s Publications Collection

Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes, limiting generality. We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation. The student model learns to synthesize motions from text alone, while the teacher leverages auxiliary signals (e.g., MANO parameters) to provide structured guidance during training. A co-training strategy enables the student to benefit from the teacher’s intermediate predictions while remaining text-only at inference. Evaluated using two diffusion backbones on GRAB and H2O, …

Autonomous Deficiency Detection And Vision-Language Summarization For Underground Infrastructure On Embedded Edge Systems, Johny Lopez

LSU New Orleans Theses and Dissertations

Aging underground infrastructure poses significant risks to public health and environmental safety, yet structural condition assessment remains bottlenecked by labor-intensive manual CCTV inspections. This thesis proposes a comprehensive algorithmic framework enabling fully autonomous, real-time deficiency detection, geometric assessment, and natural language reporting on resource- constrained edge computing platforms. Three core components address this challenge. First, RAPID-SCAN, a novel semantic segmentation architecture utilizing a Dynamic Feature Pyramid Network and Channel-Spatial Attention, achieves real-time, pixel-precise defect localization with dramatically reduced parameters. Second, an Edge-Optimized Vision-Language Model pipeline employing LoRA and 4-bit QLoRA quantization compresses Phi-3.5 for local deployment, en- abling autonomous technical …

From Data Digitization To Personalized Care: Deep Learning And Decision Analytics In Healthcare Systems, Ahla Ko

Graduate Theses and Dissertations

This dissertation traces a progression from foundational data infrastructure to individualized clinical decision-making, developing and evaluating three computational frameworks that advance healthcare efficiency and personalization through deep learning and decision analytics. The first study presents an end-to-end pipeline for automated recognition of handwritten medical forms, addressing persistent challenges in health data digitization. Integrating a YOLO-based field detection model, a Convolutional Recurrent Neural Network (CRNN) for text transcription, and a confidence-based human-in-the-loop quality assurance framework, the system achieved 99.75\% Exact Match Accuracy and a 0.13\% Character Error Rate on medical forms collected from a tuberculosis research project in Moldova. A GPU-accelerated …

Federated Neuromorphic Intelligence: Advancing Robustness, Efficiency, And Continual Adaptation In Edge Environments, Manh V. Nguyen

Dissertations

This dissertation investigates how spiking neural networks (SNNs) can improve federated edge intelligence by advancing three interconnected goals: communication efficiency, adversarial robustness, and continual adaptation. As edge computing deployments expand across Internet of Things (IoT), sensing, and privacy-sensitive applications, conventional federated learning approaches built around artificial neural networks (ANNs) face growing limitations in power consumption, bandwidth demand, and resilience to real-world uncertainty. SNNs offer an alternative computational paradigm based on event-driven, sparse, and temporally structured processing that is naturally suited to constrained edge environments. However, their behavior in practical federated settings remains insufficiently understood.

To address this gap, this dissertation …

Privacy Protection In Machine Learning: Methods For Structured And Unstructured Data, Karuna Bhaila

Graduate Theses and Dissertations

As machine learning models become increasingly integrated into data-driven decision-making, the protection of sensitive information throughout the model lifecycle is a paramount concern. As these models process and memorize sensitive, proprietary, or personal data, they risk leaking information through their outputs or internal states, especially in domains such as healthcare and finance. The protection of data in machine learning has thus been a crucial field of study. Within this paradigm, researchers have studied theoretical and application-oriented mechanisms for realizing privacy protections for various data formats. Nonetheless, privacy in machine learning still has many open problems, especially with the emergence of …

Uncertainty In Neural Networks: An Interval Approach, Yahriel Isaac Guel

Open Access Theses & Dissertations

Neural networks produce predictions but not reliable measures of how much to trust them. A clinician handed an output such as "97% chance malignant" has no way to tell whether that 97% reflects the model's actual reliability on inputs like this one, or whether the same number would have appeared on an image the model has no business classifying. The standard approaches to uncertainty quantification - Bayesian neural networks, deep ensembles, and Monte Carlo dropout - are useful. However, sometimes the uncertainty we need to handle only comes as lower and upper bounds. This raises a natural question: what if …