Computer Engineering Commons^™

Training Data Privacy In Machine Learning: A Systematization Of Attacks And Defenses, Mohammad Sufyaan Saeed

Computer Science and Engineering Theses - Archive

Training and deploying Machine Learning (ML) models introduce significant data confidentiality risks, as modern models can inadvertently memorize and leak information about their training data. While attacks such as membership inference and model inversion are well studied, the literature remains fragmented, with inconsistent threat models and unclear relationships across attack classes and defenses. This work presents a Systematization of Knowledge (SoK) that unifies the landscape of training-data privacy attacks and defenses, aligning them with the NIST Adversarial Machine Learning (AML) taxonomy to enable standardized threat modeling and comparison. Our analysis shows that, despite significant progress in characterizing attack vectors, defenses …

Methods Of Optimizing Storage And Retrieval Of Structured Data, Neelim Haider

Computer Science and Engineering Theses - Archive

Storing and retrieving large amounts of data reliably is becoming more and more important as time goes on. There are high demands to store highly personal information such as social security numbers, bank account information, and residence information to rapidly changing data such as employee information, inventory information, and stock information. Therefore, the ability of a system to store, remove, and update such information efficiently and correctly is critical. There are different types of data that database systems can potentially hold: structured, unstructured, and semistructured data. Various database models have been developed to provide a framework that allows designers to …

Transformer And Recurrent Architectures For Dynamics Prediction And Policy Learning On Long-Horizon Tasks, Vinal Jitendrabhai Gadhiya

Computer Science and Engineering Theses - Archive

Model-based reinforcement learning promises improved sample efficiency by learning environment dynamics and using them for planning or policy improvement. However, the choice of neural architecture for dynamics prediction significantly impacts the model's ability to capture temporal dependencies and maintain long-term context, capabilities crucial for complex, open-world environments.

This thesis investigates three neural architectures for learning world models: Transformer-based, GRU-based, and a hybrid Transformer+GRU approach. We evaluate these architectures on Crafter, a 2D open-world survival environment that requires long-horizon planning and sequential task completion. In Crafter, agents must perform hierarchical sequences of actions, such as collecting wood, placing a table, and …

Diversity-Driven Xor Secret Sharing: Reliable And Secure Multi-Path Transmission, Richard M. Olu Jordan

Computer Science and Engineering Theses - Archive

The growing reliance on distributed storage and multipath communication sys- tems has intensified the need for security mechanisms that remain robust even when individual nodes or channels are compromised. Secret sharing provides an information- theoretic approach to achieving both confidentiality and availability, and XOR-based constructions in particular offer lightweight and highly structured designs. This thesis develops a unified analytical framework for understanding and evalu- ating XOR-based secret sharing schemes across multiple operational settings, includ- ing plaintext storage, encrypted-data scenarios, and noisy binary symmetric chan- nels (BSCs). Building on a general (t, n) system model, we examine five threshold configurations—(2, 3), …

Multi-Modal Model-Based Optical Flow Estimation For Event-Based Vision, Pritam Karmokar

Computer Science and Engineering Dissertations - Archive

Event cameras offer a fundamentally different sensing paradigm by asynchronously capturing brightness changes at high temporal resolution, directly encoding motion in the scene. However, their sparse and non-traditional data format poses significant challenges for dense motion estimation, particularly in the context of optical flow. Contrast Maximization (CM) has emerged as a powerful model-based framework for estimating optical flow from event data by optimizing the sharpness of motion-compensated event representations. This dissertation builds upon and significantly advances the CM framework through two complementary contributions.

First, we propose Edge-Informed Contrast Maximization (EINCM), a hybrid approach that augments the traditional events-only CM framework …

An Slo-Aware, Multi-Pronged Approach To Enhancing Resource And Energy Efficiency In Server Applications, Ning Li

Computer Science and Engineering Dissertations - Archive

Server applications operating in oversubscribed cloud environments face the dual challenges of meeting strict Quality-of-Service (QoS) requirements and improving resource and energy efficiency. As the number of user connections and workload diversity continue to grow, existing scheduling mechanisms struggle to balance QoS guarantees, fairness, resource efficiency, and power consumption. This dissertation presents a unified, cross-layer framework to address these challenges through three key contributions: AppleS, UTSLO, and REEF.

First, we propose AppleS, a user-space QoS-aware fine-grained I/O scheduling framework that delivers fair and efficient service to concurrent client connections. AppleS introduces a QoS-centric metric that guides admission control and scheduling …

Deep Neural Network Models For Heatsink Performance Prediction And Optimization In Single Phase Immersion Cooling: Framework For Future Design Tools And Digital Twin Integration, Braxton J. Smith

Mechanical and Aerospace Engineering Theses - Archive

The rapidly rising computational power of modern computing components combined with the advanced packaging techniques being implemented has resulted in exponentially increasing thermal design powers (TDP) from CPUs and GPUs. Traditional air-cooling methods are approaching their effective cooling limits for many of these components, requiring lower supply air temperatures, higher supply air flowrates, and much larger heatsinks to remain feasible. Transitioning from air-cooling to single-phase immersion cooling offers numerous benefits in thermal performance, data-center size reduction, and energy efficiency. To leverage the merits of immersion cooling, the performance of a given heatsink must be predicted and optimized for best performance …

An Intelligent Robotic System For Multi-Sensory Cognitive Fatigue Detection To Assist Persons With Paralysis In Activities Of Daily Living, Enamul Karim

Computer Science and Engineering Dissertations - Archive

Assistive robotics is a promising area for improving the quality of life of people with paralysis, specifically through assistance in Activities of Daily Living (ADLs). Current state-of-the-art assistive robotic systems do not have the capability to dynamically modulate their functionality according to the cognitive fatigue level of the user, which can negatively impact their effectiveness and usability in real-life settings.

This dissertation explores an adaptive robotic framework that adjusts its behavior depending on the cognitive fatigue level of users. The system operates in three different modes, and switches between Fully Controlled, Semi-Autonomous, and Fully Autonomous modes. The overall goal is …

Fair And Sustainable Machine Learning: A Holistic Approach To Data Quality, Efficiency, And Resource-Aware Training, Zahidur Rahim Talukder

Computer Science and Engineering Dissertations - Archive

The increasing reliance on distributed, privacy-sensitive data has driven the emergence of Federated Learning (FL) as a transformative paradigm for collaborative machine learning. By enabling multiple client devices to train a shared global model without transferring raw data, FL offers significant privacy advantages. However, real-world deployments of FL are constrained by critical challenges such as data heterogeneity, client unreliability, and hardware disparities. These factors lead to uneven model convergence, degraded global accuracy, and fairness issues that threaten FL's scalability and inclusivity in diverse environments.

This dissertation investigates these challenges and proposes three novel algorithmic frameworks to advance the state-of-the-art in …

Exploring Emerging Memory Technologies For Enhancing Data Center Applications, Zhen Lin

Computer Science and Engineering Dissertations - Archive

The rapid evolution of memory and storage technologies is fundamentally reshaping the design of operating systems and data management. Emerging devices such as persistent memory, NVMe SSDs, and Compute Express Link (CXL)--enabled hybrid memory modules introduce new opportunities for high-performance, cost-efficient data management, yet they also expose limitations in traditional software abstractions. File systems, originally designed for slow block-based devices, incur excessive overhead on ultra-low-latency media, while block-level caches suffer from metadata and eviction inefficiencies. Moreover, hardware-managed tiering provides transparency but restricts adaptability across workloads. These challenges highlight the need to rethink caching and tiered memory management across multiple system …

Advancing Machine Learning Approaches Through Robust Methodologies In Llm Code Generation, Adversarial Text Classification, And Unsupervised Learning, Anahita Samadi

Computer Science and Engineering Dissertations - Archive

This dissertation combines insights across text, code, and image modalities to advance the robustness, efficiency, and adaptability of machine learning models. Specifically, we address challenges like adversarial vulnerability in text, the impact of test strategies on code generation, and dimensionality in image representation in unsupervised learning domain. These efforts highlight pipelines for designing machine learning systems that are not only efficient, but also adaptable to complex environments. In addition, these efforts together help form the basis for a multimodal AI capable of thriving in medical applications that this dissertation prototypes for future efforts.

Optimizing Architecture And Software For Next-Generation Memory Systems, Lingfeng Xiang

Computer Science and Engineering Dissertations - Archive

The rapid advancement of memory technologies presents new challenges and opportunities for system software and architectural design. This dissertation investigates how to optimize modern computing systems for next-generation memory, mostly focusing on persistent memory and Compute Express Link (CXL)-based memory. First, we conduct a detailed characterization of Intel Optane DC Persistent Memory, identifying the distinct behaviors of its on-DIMM read and write buffers and analyzing their impact on application performance. These insights motivate optimizations that decouple read and write paths, revealing that random read latency—especially in pointer-chasing workloads—is a dominant performance bottleneck. Second, we present NOMAD, a page management framework …

Medical Ai: Solving Healthcare Challenges And Inspiring Ai Innovation, Xiaowei Yu

Computer Science and Engineering Dissertations - Archive

Artificial Intelligence (AI) is transforming healthcare by enabling large-scale analysis of medical data and integrating multimodal information for more comprehensive diagnostics. I present my work addressing fundamental and challenging problems in developing state-of-the-art AI models for medical data analysis, including multimodal brain data and other medical datasets. Additionally, I design brain-inspired AI models by integrating insights from organizational principles of brain networks. Specifically, my research tackles three critical aspects: (1) AI in Computational Neuroscience, where I design deep learning models for brain network analysis to uncover the organizational principles of brain networks; (2) Brain-Inspired AI, where I integrate superior brain …

3d Perception, Mapping, And Navigation For Mobile Cobot, Tuan T. Dang

Computer Science and Engineering Dissertations - Archive

Service robots are migrating from tightly controlled factory lines into offices, hospitals, and homes, where they must perceive, remember, and act amid people, clutter, and perpetual change. Humans solve this daily by forming compact, task-relevant “cognitive maps”: we sample just enough sensory detail to guide the moment, stitch those snapshots into a sparse topological scaffold, and continuously refine it as we move. Guided by that insight, this dissertation proposes a biologically inspired mapping framework that turns partial RGB-D observations into a hybrid temporal-spatial memory—locally metric for centimeter-scale navigation yet globally topological for room-to-building navigation. The system first distills raw depth …

Breaking Granularity Barriers: Overcoming I/O Abstraction Limitations For High-Performance Storage Systems, Chen Zhong

Computer Science and Engineering Dissertations - Archive

Modern storage hierarchies exhibit performance differences spanning eight orders of magnitude. Each tier in the hierarchy presents fundamentally different optimal access sizes and patterns. Most systems read and write data in fixed-size units across different tiers, typically power-of-2 sizes. It simplifies data management but also suffers from large write amplification when handling small accesses in many real-world workloads. This fundamental disconnect between fixed-size I/O design assumption and real-world usage patterns represents the core challenge.

The storage community has recognized the limitations of fixed-size I/O abstractions and is exploring alternatives, like the new emerging NVMe-KV interface and object-based storage, which aim …

Environment And Intention Awareness For Navigation And Collaboration, Bhaskar Chandra Trivedi

Computer Science and Engineering Dissertations - Archive

Unmanned Aerial Systems (UAS) have become increasingly popular as versatile platforms for tasks such as surveillance, inspection, delivery, and maintenance. In many applications, UAS operate in environments frequented by people or containing sensitive infrastructure, which introduces physical risks in case of vehicle failure, as well as psychological and privacy concerns that may limit their acceptability. Ensuring safe and efficient operation thus requires that UAS consider these risks when planning navigation strategies. While prior information, such as city maps and building layouts, can partially inform risk assessment, such data is often incomplete, necessitating real-time augmentation of risk maps using sensor information. …

Insights In Cybersecurity Of A Smart Campus - A Review, Mircea Ţălu

Journal of Cybersecurity Education, Research and Practice

The profound impact of the Internet of Things (IoT) on various fronts, is driven by technological advancements, the ubiquitous spread of information, and the emergence of transformative events. IoT presents a diverse array of possibilities within university environments, fostering a more connected and enhanced educational experience. This research undertakes a comprehensive review of existing literature to provide context to the IoT and underscore its crucial significance in the realm of smart campuses. Additionally, the paper explores the intricate connections between IoT and key concepts such as cybersecurity and wireless sensor networks to present a holistic perspective. It delves into the …

Crop2cloud Platform: Real-Time Data Integration For Agricultural Water Monitoring, Bryan Nsoh, Abia Katimbo, Kendall Dejonge, Wei-Zhen Liang, Hongzhi N. Guo, Yufeng Ge, Derek M. Heeren, Yeyin Shi, Xin Qiao, Daran R. Rudnick, Hope Njuki Nakabuye, Birru Girma, Isa Kabenge, Joshua Wanyama

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Efficient water management is vital for sustainable agriculture, yet integrating real-time data for precise irrigation remains a challenge. This study designed the Crop2Cloud (C2C) platform, a system that leverages advanced sensors using Internet of Things (IoT), edge and cloud computing techniques, and computed Water Stress Indices (WSIs) and machine learning models (i.e., fuzzy logic), to provide scalable and real-time irrigation decisions. The C2C platform aggregates several data including Volumetric Water Content (VWC) from TDR sensors (Acclima Inc., US) installed at four multiple depths, canopy temperatures (Tc) measured by Infrared Radiometers (IRTs) (Apogee Instruments, US), as well as weather information and …

Examining Terraform And Bicep: A Comparative Analysis Of Infrastructure As Code Tools For Provisioning Azure Environments, Richard Coffey, Kevin Bayliss

Academic Poster Collection

Examining Terraform and Bicep: A Comparative Analysis of Infrastructure as Code Tools for Provisioning Azure Environments

The Business-Day Cloud: A Hybrid Kubernetes And Serverless Solution For Sustainable Scaling With Predictable Load Patterns, Brendan Burnside, David White

Academic Poster Collection

The Business-Day Cloud: A Hybrid Kubernetes and Serverless solution for Sustainable Scaling with Predictable Load Patterns