Computer Sciences Commons^™

Improving Fairness On Semantic Segmentation Using Large Language Models, Samuel E. Burggraf

Electrical & Computer Engineering Projects for D. Eng. Degree

As machine learning systems are increasingly integrated into critical decision-making processes, ensuring fairness in their design and implementation has become a significant concern. While fairness research has primarily focused on specific protected attributes, less attention has been given to spatial fairness, which can affect individuals at specific locations. If fairness is not addressed, models may systematically underperform in certain regions or across populations which can lead to unequal access to accurate predictions and potentially biased decision-making. Fairness considerations should extend across all machine learning applications to align with the National Institute of Standards and Technology (NIST) guidelines of fair and …

Temperature-Induced Uncertainty In Fixed-Context Retrieval-Augmented Generation, Steven Zeng, Murat Kuzlu

Cybersecurity Undergraduate Research Showcase

This study examines how decoding temperature affects output uncertainty in a fixed-context retrieval-augmented generation (RAG) system. We define uncertainty as the semantic dispersion among repeated answers under the same fixed retrieved context, with greater dispersion interpreted as higher uncertainty. To isolate this answer-generation variability from retrieval drift, each question was paired with a fixed retrieved context, and repeated generations differed only in temperature. The experiment used nine questions drawn from a machine-learning textbook corpus, with three questions each at easy, moderate, and hard difficulty. Each question was evaluated at five temperatures (0.0, 0.25, 0.5, 0.75, and 1.0) over 30 iterations, …

Phishing Restraint: University Simulated Phishing Campaigns, Alexander M. Abou Khir

Cybersecurity Undergraduate Research Showcase

Universities face heightened vulnerability to phishing attacks due to their open information-sharing culture and diverse user populations. This study examines how phishing exploits human factors within campus environments and evaluates three major training strategies: embedded phishing, microlearning, and role-based instruction to understand their individual and combined effectiveness. I explored studies that implement these strategies in pairs and use the strategies alone, identified trends in susceptibility reduction, behavioral reinforcement, and contextual relevance. I suggest that, while each method independently improves user awareness, multiple approaches offer stronger, more adaptable protection by addressing both psychological triggers and role-specific risks. The paper contributes a …

Hijacking The Prompt: A Survey Of Prompt Injection Attacks, Detection, And Defense In Large Language Models, Edward J. Griggs

Cybersecurity Undergraduate Research Showcase

Prompt injection attacks, ranked the number-one vulnerability in AI systems by OWASP's 2025 Top 10 for Large Language Model Applications, remain largely unsolved, and this survey examines why. As large language models (LLMs) are deployed across enterprise workflows, agentic systems, and consumer tools, their fundamental inability to distinguish trusted instructions from untrusted user data has created a persistent and expanding attack surface. This paper presents a structured taxonomy of prompt injection attack vectors, including direct injection, indirect injection, multimodal attacks, tool and agent exploitation, hybrid chained techniques, and autonomous propagating threats. These vectors are mapped across five impact categories (data …

Limitations Of Signature-Based Network Intrusion Detection Under Modern Traffic Conditions, Henry Guidry

Cybersecurity Undergraduate Research Showcase

Network Intrusion Detection Systems are tools used to monitor network traffic and alert to suspicious or harmful activity before it can cause harm. Signature-based versions of these systems are a foundation for intrusion detection, operating by finding common patterns and forming malicious signatures. However, three developments in modern network environments have greatly impacted the significance of Network Intrusion Detection Systems. These three developments are the near-complete adoption of end-to-end encryption, the use of sophisticated packet fragmentation techniques, and the processing demands of high-throughput networks. Encryption makes deep packet inspection practically infeasible by transforming inspectable payloads into ciphertext, forcing NIDS to …

Artificial Intelligence Moderation In Online Gaming: A Cybersecurity Analysis Of Risks And Defenses, Labib Khan

Cybersecurity Undergraduate Research Showcase

This research paper will examine the role of artificial intelligence (AI) moderation systems in enhancing cybersecurity within online gaming environments. As multiplayer platforms increasingly rely on real-time text, voice communication, and user-generated content, developers have implemented AI-driven tools such as natural language processing (NLP), speech recognition, and behavioral analytics to detect harassment, toxic behavior, cheating coordination, and other malicious activity. These systems enable gaming companies to efficiently monitor large volumes of player interactions, improving response times and helping maintain safer and more controlled digital environments for users across global gaming communities of varying sizes and activity levels.

While these technologies …

Escaping Isolation: An Analysis Of Virtual Machine And Container Breakout Vulnerabilities, Felix Iov

Cybersecurity Undergraduate Research Showcase

Cloud computing providers rely on multi-tenant architectures to maximize resource efficiency. This infrastructure depends on virtualization, which provides isolation between clients. This comes primarily in the form of Virtual Machines (VMs) and Containers. However, “breakout attacks” or “escapes” are a critical threat where attackers bypass these isolation layers to gain unauthorized access to the host system and neighboring environments. This paper surveys virtualization escape threats and analyzes three case studies: a runc container escape (Leaky Vessels), a VMware ESXi VM escape (VSOCKPuppet), and an NVIDIA GPU container escape (NVIDIAScape). Each demonstrates different attack surfaces, including file descriptor misuse, kernel driver …

Bio-Cybersecurity: Securing The Healthcare Industry, Amanda D. Coleman

Cybersecurity Undergraduate Research Showcase

Bio-cybersecurity refers to the aspect of cybersecurity that applies to the biological sciences and the protection of digital biomedical information. Today’s healthcare industry has evolved with the enhancement of internet and biomedical technology. While hospitals and private medical providers remain compliant with the Health Information Portability and Accountability Act (HIPAA) through traditional means of securing documented patient information, the emergence of beneficial internet-based healthcare services like virtual appointments and digital patient records requires new policies and healthcare cybersecurity frameworks to protect sensitive information from unauthorized access. This paper examines the role of cybersecurity in healthcare, the vulnerabilities that exist and …

Ai's Double Edged Sword: Fighting Against Synthetic Csam, Shekhinah Adra Green

Cybersecurity Undergraduate Research Showcase

The rapid advancements in generative artificial intelligence has introduced new challenges in the production and distribution of synthetic child sexual abuse material (CSAM). AI has the capabilities of creating highly realistic imagery and videos, which  raises serious legal and ethical concerns, increasing the risk of harm, exploitation, and revictimization.

This paper discusses the legal improvements needed in order to lower the change of legal loopholes, how digital forensic analyst use advanced tools to identify and investigate synthetic material, and different methods to start the reduction of synthetic CSAM.

Personality Predictors Of Cybersecurity Vulnerability: Insights From Self-Reports And Stimulated Threat Scenarios, Saroja Roy Grandhi

Psychology Theses & Dissertations

In this cyber dependent and enabled era, understanding the role of human factors in digital security is essential. This study investigates the relationship between Big-Five personality traits and cybersecurity behaviors by examining both self-reported and stimulated behaviors in security threat scenarios. Participants completed validated questionnaires to report their personality traits, cybersecurity practices and engage in task-based stimulations to capture behaviors such as phishing detection, password creation, and response to security alerts. The study tested whether higher conscientiousness, openness, and agreeableness would be associated with stronger cybersecurity practices and smaller discrepancies between self-reported and observed behaviors. And, whether greater extraversion and …

Pushing High-Performance Private Inference Towards Resource-Constrained Edge Clients, Xiangrui Xu

Computer Science Theses & Dissertations

The widespread adoption of Machine Learning as a Service (MLaaS) has enabled resource constrained edge clients, such as mobile and IoT devices, to leverage powerful deep learning mod els hosted on the cloud. However, this paradigm introduces critical privacy challenges regarding the client’s sensitive input data and the server’s proprietary model parameters. While cryptographic techniques like Homomorphic Encryption (HE) and Multi-Party Computation (MPC) enable Private Inference (PI), existing frameworks impose prohibitive computational and communication overheads that render them impractical for edge deployment. This dissertation introduces three novel frameworks—SPOT, LUTless, and PrivShap—to systematically address the efficiency bottlenecks of PI in edge …

Behavioral, System, And Informational Cyberattacks: A Human-In-The-Loop Driving Simulator Experiment, Samuel Petkac

Psychology Theses & Dissertations

Advanced technologies such as sensors and AI/ML algorithms have enabled increasing levels of automated driving system that detects, responds, and even predicts changes in a driving environment supported by wireless connectivity to nearby vehicles and infrastructure. Such connected and automated vehicles (CAVs) can be particularly vulnerable to cyberattacks targeting not only infotainment systems but also firmware and other applications, critically compromising driver safety. As we anticipate a “mixed” traffic where vehicles with various levels of automated technologies share the road for the foreseeable future, it is urgent to systematically examine types of possible cyberattacks and control human behaviors in such …

Optimization Of Niobium Film For Particle Accelerators And Quantum Applications, Bektur Abdisatarov

Electrical & Computer Engineering Theses & Dissertations

Niobium (Nb) films play a central role in superconducting technologies used in particle accelerators and superconducting quantum circuits. Optimizing the physical properties of Nb films is therefore critical for improving both radiofrequency (RF) performance in superconducting radiofrequency (SRF) cavities and coherence in superconducting qubits. This thesis investigates the relationship between Nb film microstructure, impurity content, and electromagnetic response across these two application domains.

For particle accelerator applications, we studied Nb films deposited using high-power impulse magnetron sputtering (HiPIMS) with DC bias onto a 1.3 GHz elliptical SRF cavity. Nb film cavities exhibit a pronounced medium-field Q-slope, limiting their achievable accelerating …

The Psychology Behind Ai-Generated Phishing And Social Engineering Attacks, A’Shya Reynolds

School of Cybersecurity Master's Level Projects and Papers

Cybercrime has evolved significantly with the integration of artificial intelligence (AI), transforming traditional phishing and social engineering attacks into highly sophisticated and personalized threats. While early phishing attempts relied on generic messaging and low success rates, modern AI-driven attacks leverage advanced data analytics, natural language processing, and behavioral prediction to manipulate victims more effectively.

This research examines how cybercriminals utilize AI to enhance psychological manipulation techniques in phishing and social engineering attacks, increasing victim susceptibility. Drawing from interdisciplinary literature in cybersecurity and psychology, this study explores key psychological mechanisms, including cognitive biases, emotional triggers, and decision-making processes that influence victim …

Dissecting The Etiology Of Alcohol Use Disorder By An Integrative Heritable Component Approach, Ivy Garrenton

Computer Science Theses & Dissertations

Alcohol Use Disorder (AUD) is a pervasive condition characterized by complex interplay among genetic, phenotypic, and environmental factors. Although previous studies have identi fied genetic loci associated with alcohol consumption, these efforts have not captured the genetic heterogeneity and gene-environment interactions underlying AUD pathogenesis. To address this critical gap, we developed a novel statistical methodology that integrates phenotypic, genotypic, and environmental data through an environmentally modified Genetic Relationship Matrix (GRM) to derive AUD-related traits with enhanced heritability.

This approach demonstrated superior performance in both simulated and real-world datasets. Traits derived using the environmentally modified GRM exhibited significantly higher estimated heritability …

Learning Techniques In Prediction Of Functional Epigenomic Events, Mohammad Shiri

Computer Science Theses & Dissertations

Accurately predicting functional epigenomic events from DNA sequences is critical to understanding gene regulation and the functional impact of non-coding variants. Despite considerable progress, critical challenges hamper the effectiveness and efficiency of existing deep learning approaches. These challenges include negative transfer in multi-task learning (MTL), suboptimal network architectures, and pervasive label noise, particularly the positive-unlabeled problem arising from data sparsity in single-cell assays. This dissertation presents a cohesive framework of novel learning techniques to effectively address these challenges. First, a highly scalable task grouping framework is presented to mitigate negative transfer in deep MTL. This method clusters tasks based on …

Pong Revised: Network-Based Competitions Through Secure Socket Services, Noah T. Jennings, Destiny D. Hale, Jared D. Williams, Michael J. Lively-Scholz

Knowledge and Creativity Expo

We aim to provide a safe, thrilling, locally hosted, and educational multiplayer experience that can be quickly replicated in modern Capture The Flag (CTF) events.

How Much Does Shape Matter: Investigating The Impact Of Marine Particle Morphological Features On In-Situ Settling Velocities Using Pca And Various Ml Models, Huanqing Huang, Alexander B. Bochdansky

Knowledge and Creativity Expo

Particle settling velocity serves as an essential component in ocean biological pump, as it determines particle retention time in the water column. Stokes’ law has been widely used to predict particle settling velocities by particle size and excess density in aquatic environments. However, an increasing number of studies suggest that Stokes’ law fits poorly in the size-velocity relationship of observations on small oceanic particles. Here, we present a series of novel approaches to investigate the relative contribution of settling velocities by the particle shape and optical densities using machine learning (ML) models and principal component analysis (PCA), based on 3906 …

Human Subject Studies For The Alignment Of Llm-As-A-Judge Evaluation Metric For Science News, Gabriel Vega Osborne

Knowledge and Creativity Expo

Science news has become an important vehicle to disseminate scientific breakthroughs, discoveries, and technological innovations. With the advancement of large language models and related AI models, it is possible to automatically generate science news from scientific papers, extending the reader population from domain scientists to a broader scope. However, how to evaluate the quality of the generated news warrants research. Traditional token based metrics have been shown to fail to evaluate the semantics and nuances of science news. Inspired by the fact that a major goal of science news is to educate readers with new knowledge, we thus propose knowledge …

A. Vs. I In Ai: Is There A Threshold To "Engineered" Intelligence?, Joshit Mohanty

Engineering Management & Systems Engineering Faculty Publications

Despite artificial intelligence reshaping the world, its development generates uncertainties regarding future capabilities. AI simultaneously exists as an artifact of engineering design and as autonomous intelligence, creating an observer-participant feedback loop. This paper proposes that embodied AI faces a bandwidth-limited intelligence threshold T_h that it arises from B = min(C_sens,C_Act). However, Shannon capacity measures bits while intelligence operates on concepts, necessitating a dual-channel model separating physical bandwidth B_io from representational capacity B_rep. Intelligence emerges as multi-dimensional rather than scalar, with components exhibiting different bandwidth dependencies. Surpassing T_h requires either new sensing methods expanding B, enhanced representational frameworks, or reconceptualization within …

Aura: An Ai-Powered Multimodal Prototype For Adaptive Apraxia Of Speech Therapy And Communication Support, Omotayo Omoyemi, Rachel K. Johnson

Speech-Language Pathology Faculty Publications

Apraxia of Speech (AOS) is a motor speech disorder that significantly limits communication and requires intensive, long-term therapy. Access to consistent treatment is often constrained by shortages of speech-language pathologists, high costs, and limited opportunities for continuous monitoring outside clinical settings. Recent advances in Artificial Intelligence (AI) provide new opportunities to support scalable and personalized speech therapy.

This paper presents AURA (Adaptive Understanding and Relearning Assistant for Apraxia), a multimodal AI framework designed to support speech therapy, progress monitoring, and communication for individuals with AOS. The system integrates speech analysis, machine learning–based error detection, reinforcement learning for adaptive therapy, and …

Part Ii: Industrial Information Integration Review 2020-2025, Jinzhi Li

Information Technology & Decision Sciences Faculty Publications

Industrial Information Integration Engineering (IIIE) has become increasingly essential for improving operational efficiency and harmonizing heterogeneous industrial systems through advanced digital integration approaches. Fueled by rapid advancements in Industry 4.0 technologies—including digital twins, artificial intelligence, immersive interfaces, and IoT infrastructures—IIIE is substantially transforming traditional enterprise architecture and integration frameworks. This systematic review synthesizes recent developments and emerging trends, with particular attention to the accelerating adoption of digital twins and the deepening convergence between operational technologies (OT) and information technologies (IT) across multiple sectors. While notable progress has been made, significant challenges persist, especially in developing resilient integration architectures and fully …

Counseling Professionals' Perspectives On Ai Integration In Education And Supervision: A Concept Mapping Study, Hank Crofford, Elif Bor, Gülşah Kemer

Counseling & Human Services Faculty Publications

The rapid emergence of artificial intelligence (AI) has raised important questions about how new technologies will shape professional norms and practices in counseling. The purpose of this study was to understand how counseling professionals expect AI to be integrated into counselor education and supervision (CES). Using a mixed‐methods concept mapping design, 31 participants generated and sorted statements about the potential roles, benefits, and concerns associated with AI in the profession. Participants represented diverse counseling roles, including counselor educators, licensed professional counselors, supervisors, master's‐ and doctoral‐level trainees, and other counseling‐related professionals. Standard concept mapping procedures were conducted using R, resulting in …

A Macrocognitive Design Taxonomy For Simulation-Based Training Systems: Bridging Cognitive Theory And Human-Computer Interaction, Jessica M. Johnson

Virginia Digital Maritime Center (VDMC) Faculty Publications

Simulation-based training systems are increasingly deployed to prepare learners for complex, safety-critical, and dynamic work environments. While advances in computing have enabled immersive and data-rich simulations, many systems remain optimized for procedural accuracy and surface-level task performance rather than the macrocognitive processes that underpin adaptive expertise. Macrocognition encompasses higher-order cognitive processes that are essential for performance transfer beyond controlled training conditions. When these processes are insufficiently supported, training systems risk fostering brittle strategies and negative training effects. This paper introduces a macrocognitive design taxonomy for simulation-based training systems derived from a large-scale meta-analysis examining the transfer of macrocognitive skills from …

A Hybrid Response Surface Methodology And Machine Learning Framework For Quantifying Effects Of Physicochemical Parameters On Pfas Distribution, Harsh V. Patel, Jazmin Green, Hyoshin Park, Stephanie Luster-Teasley Pass, Renzun Zhao

Engineering Management & Systems Engineering Faculty Publications

Predicting PFAS adsorption across diverse adsorbents and environmental matrices remains challenging because adsorbent physicochemical properties, PFAS molecular descriptors, and operational conditions simultaneously influence adsorption. This study develops and evaluates a unified hybrid modeling framework that integrates Response Surface Model (RSM) with machine-learning algorithms to quantify how six key variables, surface area, Log K_ow, pH_pzc, pK_a, log dose, and log-initial concentration, affect PFAS distribution coefficients (Log K_d). A data set of more than 1000 adsorption observations spanning 15 PFAS compounds, multiple adsorbent types, and a broad operational range was compiled and preprocessed using …

Crossing The Theory Threshold: The Pedagogical Potential Of Generative Artificial Intelligence In Educational Research, Amanda Burbage, Jennifer L. Styron

EVMS School of Health Professions Faculty Publications

Purpose

This paper presents findings from an educational research graduate course in which generative artificial intelligence (AI) was incorporated to strengthen learners' understanding of threshold concepts related to theoretical frameworks. Medical and health professionals often struggle with the transition from a clinical role into the educational research role.

Methods

The study posits that the use of generative AI will help learners understand and apply theoretical frameworks beyond a superficial level, furthering their understanding, constructing new knowledge, and strengthening their ability to develop sound educational research studies. Journal and AI transcripts were analyzed for 37 participants.

Results

Open-ended codes were grouped …

Use Of Tezepelumab For Chronic Rhinosinusitis With Nasal Polyps By Eosinophilic Endotype: Waypoint Post-Hoc Analysis, Shigeharu Fujieda, Nobuyoshi Otori, Joseph K. Han, Tadataka Yabuta, Claudia Chen, Claudio Marchese, Andrews Foster, Sandhia S. Ponnarambil, Yun Chan, Brian J. Lipworth

Department of Otolaryngology (ENT) Faculty Publications

Background

The phase 3 WAYPOINT study (NCT04851964) reported that tezepelumab improved outcomes in patients with chronic rhinosinusitis with nasal polyps (CRSwNP), including nasal polyp size, nasal congestion, and sinonasal symptoms, and reduced the need for surgery and systemic corticosteroids (SCS).

Objective

To evaluate the efficacy and safety of tezepelumab across Japanese Epidemiological Survey of Refractory Eosinophilic Chronic Rhinosinusitis-defined eosinophilic chronic rhinosinusitis (ECRS) subgroups.

Methods

Adults with severe CRSwNP were randomized to tezepelumab 210 mg or placebo every 4 weeks. Coprimary end points were the change from baseline to week 52 in total Nasal Polyp Score and the biweekly mean Nasal …

Logistic-T Multinomial Mixture Model For Clustering For Microbiome Data, Wenshu Dai, Yuan Fang, Sanjeena Subedi

Mathematics & Statistics Faculty Publications

The logistic-normal multinomial distribution has been used for modelling microbiome data obtained from high-throughput sequencing technologies, which are compositional in nature. A logistic-normal multinomial distribution is a hierarchical multinomial distribution that assumes the latent variable which are the additive log-ratio (ALR) transformed proportions in a multinomial distribution follows a Gaussian distribution. Model-based clustering algorithms have also been developed for clustering microbiome data based on the logistic-normal models. However, the Gaussian assumption may violated when the ALR transformed variable exhibit heavy-tailed distributions or has outliers. Our study introduces a novel mixture of logistic-t multinomial models that effectively address these challenges. Utilizing …

Shaping The Future: Emerging Technologies And Their Role In Industry 4.0 And Beyond, Liuliu Qin

Information Technology & Decision Sciences Faculty Publications

This paper provides a comprehensive review of emerging technologies driving the transition from Industry 4.0 to Industry 5.0. It examines the foundational concepts and pillars of Industry 4.0 and explores the transformative roles of Artificial Intelligence (AI), Extended Reality (XR), Collaborative Cobots (Cobots), Brain–Computer Interfaces (BCIs), quantum technologies, and next-generation connectivity (5G/6G). By integrating technological, human-centric, and sustainability perspectives, the study outlines how these emerging technologies reshape industrial systems and enable intelligent, adaptive, and inclusive futures.

Framework For Task Offloading In O-Ran Architecture For Heterogeneous Computing Applications, Samira Taheri, Neda Moghim, Naser Movahhedinia, Sachin Shetty

Center for Secure and Intelligent Critical Systems (CSICS) Publications

Computational offloading transfers tasks from resource-constrained devices to more capable servers or cloud platforms, improving processing speed and user experience. Open radio access networks (O-RAN's) disaggregated architecture and open interfaces make it suitable for offloading delay-sensitive tasks, enhancing real-time application performance. This study focuses on task offloading in O-RAN, a reference network architecture. Although research on O-RAN is limited, existing work lacks a comprehensive approach to offloading, including offloading layer determination, node selection, and resource allocation based on task types and their latency needs. We propose a delay-aware task offloading framework within O-RAN to support diverse delay requirements, improving offloading …