Digital Commons Network^™

General Test-Time Backdoor Detection In Split Neural Network-Based Vertical Federated Learning, Shunjie Yuan, Xinghua Li, Xuelin Cao, Haiyan Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

As a new distributed machine learning framework, vertical federated learning (VFL) has been widely applied in the industry. However, recent studies have demonstrated that VFL faces serious challenges from backdoor attacks, which significantly hinder its further development. Although a few studies have focused on defending against VFL backdoor attacks, these defenses either do not consider the latest attack methods or show limited effectiveness. Moreover, most existing backdoor defense efforts primarily focus on backdoor attacks in horizontal federated learning (HFL) and centralized learning. Due to the unique architecture of VFL models, these methods cannot be directly applied to backdoor defense in …

Kpiroot+: An Efficient Integrated Framework For Anomaly Detection And Root Cause Analysis In Large-Scale Cloud Systems, Wenwei Gu, Renyi Zhong, Guangba Yu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

To ensure the reliability of cloud systems, their runtime status reflecting the service quality is periodically monitored with monitoring metrics, i.e., KPIs (key performance indicators). When performance issues happen, root cause localization pinpoints the specific KPIs that are responsible for the degradation of overall service quality, facilitating prompt problem diagnosis and resolution. To this end, existing methods generally locate root-cause KPIs by identifying the KPIs that exhibit a similar anomalous trend to the overall service performance. While straightforward, solely relying on the similarity calculation may be ineffective when dealing with cloud systems with complicated interdependent services. Recent deep learning-based methods …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Towards Inclusive Digital Futures Of Cultural Heritage: Insights From A Critical Discourse Analysis Of Unesco Dialogues, Shiqing Huang, Keng Siau, Xiaoting Chen

Research Collection School Of Computing and Information Systems

Digital technologies are shaping many aspects of cultural heritage, but very little research has examined the implications of digital transformation. Drawing on concepts from Fairclough’s three-dimensional critical discourse analysis, this research examines the discourse using seven online dialogues (available on the UNESCO website) between 18 professionals who have different backgrounds and cultures to identify social practices related to the digital transformation of cultural heritage. We identify four digital transformation discourse types in professional dialogues: documentation, management, interpretation, and interaction. We also identify seven main groups: memory institutions including libraries, archives, and museums (LAMs), governments, international organizations, art and creative supporters, …

Cropcapsnet: Enhanced Capsule Network For Crop Disease Classification, Juan Qin, Linfan Deng, Cong Li, Junjie He, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The prevention and treatment of crop diseases are crucial for the development of smart agriculture. The classification of crop diseases based on deep learning for early disease monitoring and control has become the mainstream direction of research. This paper proposes a novel deep learning model called ”CropCapsNet”, which combines Squeeze-and-Excitation Inception (SE-Inception) module and has improved capsule structure for crop disease classification. The network first extracts shallow features of input samples through double-layer convolution, then uses SE-Inception to achieve deep multi-scale feature acquisition, and finally outputs classification results through an improved capsule structure. SE-Inception adds Squeeze-and-Excitation(SE) attention after each multi-scale …

An Intelligent Healthcare System For Rare Disease Diagnosis Utilizing Electronic Health Records Based On A Knowledge-Guided Multimodal Transformer Framework, Ahed Abugabah, Prashant Kumar Shukla, Piyush Kumar Shukla, Ankur Pandey

All Works

Rare diseases are a common problem with millions of patients globally, but their diagnosis is difficult because of varied clinical presentations, small sample size, and disparate biomedical data sources. Current diagnostic tools are not able to combine multimodal information effectively, which results in a timely or wrong diagnosis. To fill this gap, this paper suggests a smart multimodal healthcare framework integrating electronic health records (EHRs), genomic sequences, and medical imaging to improve the detection of rare diseases. The framework uses Swin Transformer to extract hierarchical visual features in radiographic scans, Med-BERT and Transformer-XL to learn semantic and long-term temporal relations …

Big Data Transfer Service Architecture For Cloud Data Centers: Problems, Methods, Applications, And Future Trends, Muhammad Umar Majigi, Ismaila Idris, Shafi’I Muhammad Abdulhamid, Richard A. Ikuesan

All Works

Data volume, velocity, and structure have significantly evolved over the years. The complex networking architectures of current infrastructures, and the development, and accessibility of cloud services to a diverse user base have introduced numerous challenges which have raised concerns regarding the quality-of-service performance in data processing for both service providers and customers. Key issues identified in the context of big data transfer services for cloud data centers include storage, big data transfer, service transfer architecture, data processing, bandwidth, and security, all of which demand extensive research. After thoroughly screening selected peer-reviewed articles, the primary open issues are: incorporating a data …

A Hybrid Fog-Edge Computing Architecture For Real-Time Health Monitoring In Iomt Systems With Optimized Latency And Threat Resilience, Umar Islam, Mohammed Naif Alatawi, Ali Alqazzaz, Sulaiman Alamro, Babar Shah, Fernando Moreira

All Works

The advancement of the Internet of Medical Things (IoMT) has transformed healthcare delivery by enabling real-time health monitoring. However, it introduces critical challenges related to latency and, more importantly, the secure handling of sensitive patient data. Traditional cloud-based architectures often struggle with latency and data protection, making them inefficient for real-time healthcare scenarios. To address these challenges, we propose a Hybrid Fog-Edge Computing Architecture tailored for effective real-time health monitoring in IoMT systems. Fog computing enables processing of time-critical data closer to the data source, reducing response time and relieving cloud system overload. Simultaneously, edge computing nodes handle data preprocessing …

A Deep Learning Framework For Automated Breast Cancer Diagnosis Using Intelligent Segmentation And Classification, Ahed Abugabah

All Works

Breast cancer is the most commonly diagnosed cancer among women worldwide, accounting for a significant proportion of new cases. Deep learning (DL) has emerged as a powerful tool for the detection and diagnosis of breast cancer, particularly through the analysis of histological images, a critical component of automated diagnostic systems that directly impact patient management. The BreakHis dataset and the Wisconsin Breast Cancer Database (WBCD) are widely used publicly available resources for deep learning–based analyses of breast cancer histological images in cross-disciplinary healthcare research. A computer-assisted approach employs colour normalisation to reduce the effects of the differences in the distribution …

Connecting The Dots: Iot, Sustainability, And Sdgs, Saadat M. Alhashmi, Islam Al-Qudah, Ibrahim Abaker Hashem, Belal Alsinglawi, Raiza Borreo, Hassan S․ Migdadi, Weisi Chen

All Works

Internet of Things (IoT) technologies can transform various sectors by converging with global sustainability goals. This paper systematically reviews how IoT supports fulfilling the United Nations Sustainable Development Goals (SDGs). This study initially identified publications that are most relevant to IoT and sustainability. Each publication was carefully examined and mapped to its corresponding SDG, methodology, context, and country. This work presents an opportunity to learn about country contributions, collaborations, and IoT and SDG research trends over the past decade. India, China, and the US were among the top contributors to the IoT and SDG literature, with India accounting for 68 …

A Picture Tells A Thousand Words—, But Ecg Signals Have More To Say, Ashley N. Gomez

Theses and Dissertations

With the increasing adoption of deep learning classification models in the medical domain, a critical challenge remains: achieving high predictive accuracy while maintaining clinical Inter-pretability. This study examines how model architecture, dataset origin, and the use of full versus subset data affect both classification performance and Interpretability in Electrocardiogram (ECG) signal analysis. ResNet18 is evaluated using an open-source ECG Image Dataset, thus a custom dataset derived from digitized ECG images. Post-hoc explainability methods, such as Integrated Gradients, are applied to determine which time steps have the most significant influence on model decisions. The findings demonstrate that model architecture and dataset …

Efficient Self-Supervised Representation Learning For Large-Scale Time Series Classification, Kevin Garcia

Theses and Dissertations

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical …

Interpretable Alignment Of Textual Weather Reports With Local Sensor Time Series For Extreme Weather Event Visualization, Juan Luis Garza

Theses and Dissertations

This thesis presents an automated and interpretable pipeline that links natural-language weather narratives with local meteorological sensor time series. Using large language models, NOAA-style event reports are transformed into structured records capturing event type, timing, descriptive context, and uncertainty. Each extracted event is aligned with harmonized temperature, precipitation, and wind measurements from nearby weather stations, enabling systematic comparisons between narrative evidence and observed atmospheric conditions.

Across roughly fifty stations and more than two thousand events, the analyses show that discrepancies between narrative descriptions and sensor behavior arise primarily from spatial separation rather than from temporal offsets, sensor preprocessing artifacts, or …

Fractals, Reachability, And Computation In Models Of Dna Self-Assembly And Chemical Reaction Networks, Ryan Arlie Knobel

Theses and Dissertations

This thesis serves as the bridge between results compiled across varying models of tile self-assembly, molecular computation, and game complexity. As such, this thesis is broken into three chapters. In the first part, we show how to generate any Discrete Self-Similar Fractal (DSSF) with a feasible generator in the seeded Tile Assembly model, a model limited to single tile attachments and pairwise state transitions. In the next part, we study models of molecular computation, where we consider the problem of reachability in Chemical Reaction Networks and similar model extensions. The final part is a game-complexity analysis of Celtic! and k-ago, …

Making Explanations Make Sense: Xai For Smishing Detection, Eleni Alexandra Katsarakes

Psychology Theses & Dissertations

Explainable Artificial Intelligence (XAI) is a key component of effective human-AI collaboration, particularly in high-stakes domains such as cybersecurity. While AI tools hold promise for mitigating threats such as SMS-based phishing (SMiShing), their real-world effectiveness may hinge not just on detection accuracy, but on whether users can make sense of the system’s outputs. As SMiShing attacks grow in both frequency and sophistication, so does the urgency of designing human-centered AI systems that support user decision-making under uncertainty. This study examined how four distinct AI explanation types - Normative (rule-based), Attributive (feature-based), Exemplar (case-based), and Recommendation-Only - influence user performance, confidence, …

Sciteuq: Toward Uncertainty-Aware Complex Scientific Table Data Extraction And Understanding, Kehinde Ajayi

Computer Science Theses & Dissertations

Scientific tables report critical research insights, data, and findings for scientific progress. Because Portable Document Format (PDF) is the de facto standard format for scientific paper publishing, there has been an emerging need for an automatic method to extract data from PDF files. A significant fraction of scientific tables exhibit complex structure and content, making it challenging for machine learning tools to accurately extract the content directly from PDF files. Despite the advancements in Table Structure Recognition (TSR), automated extraction of data from complex scientific tables remains a challenge due to variations in table structures and contents. In this dissertation, …

Large Language Models (Llms) For Clinical Note Generation: International Classification Of Disease (Icd) Code, Knowledge Graph (Kg) And Prompt Evaluation, Ivan P. Makohon

Computer Science Theses & Dissertations

In the past decade, a surge in the amount of electronic health record (EHR) data in the United States occurred, driven by a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients’ assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering them. Manually writing these notes is time-consuming, increasing patient waiting times and potentially delaying diagnoses. Large language models (LLMs), such as GPT-4o, possess the ability …

Sme Cyber Resilience State Of The Sector 2025, Hazel Murray, Gillian O'Carroll, Aoibheann Brangan, Jason Holland, Stephanie Chevanne Wallace, Miriam Curtain, Glenda Deveney

Department of Computer Science Publications

Ireland's small and medium enterprises (SMEs) face a critical cyber resilience gap. SMEs account for 99.8% of all enterprises in Ireland and employ over 2.29 million people, representing 67.9% of total employment (based on the latest CSO 2022 figures). This cyber resilience assessment reveals that the majority of SMEs remain underprepared for modern cyber threats.

Cross-Modal Prompting For Multi-Class Visual Anomaly Localization, Duncan F. Mccain

All Theses

Visual anomaly detection is a technology that uses computer vision to automatically identify defects or irregularities in images, such as cracks, scratches, or discolorations on manufactured products. Unsupervised visual anomaly detection does this without needing examples of those defects during the training process. This "unsupervised" approach is crucial in industries like manufacturing, automotive, electronics, and pharmaceuticals, where ensuring product quality is essential for safety, reliability, and cost efficiency. For instance, it helps spot flaws in circuit boards, fabrics, or medical pills during production lines, preventing faulty items from reaching consumers. By reducing manual inspections, it saves time and resources, benefiting …

Accelerating Relationship Discovery In Chronic Lower Back Pain Through Knowledge Graph And Ontology Enhanced Large Language Models, Damon Lin

Master's Theses

Chronic lower back pain (cLBP) is a widespread public health burden linked to anxiety, depression, and opioid addiction. Interventions aimed at treating cLBP have shown minimal improvements in pain outcomes, leading researchers to reexamine our understanding of cLBP through constructing a causal model. However, constructing causal models through Randomized Controlled Trials are often unfeasible, and relying on domain expertise requires extensive and time-consuming research, posing a serious bottleneck for designing effective treatments. To accelerate this process, we apply Knowledge Graphs, Ontologies, and Large Language Models (LLMs) to aid researchers in determining possible causal relationships. First, we demonstrate how LLMs can …

A Comparative Evaluation Of Feedback Strategies For Enhancing Student Software Test Suite Writing Outcomes, Ashton Alonge

Master's Theses

Background and Context

Software testing is a fundamental component of computer science education, forming the basis for students’ ability to ensure program correctness and reliability. Despite its importance, many students struggle to design test cases that effectively expose faults and achieve meaningful test coverage. Traditional instructional approaches often emphasize code coverage metrics such as line or branch coverage, but these metrics may not adequately capture the quality of student tests. Mutation analysis, which measures how well tests detect small, artificial faults (mutants) introduced into the program, offers a potentially richer measure of test effectiveness. However, little is known about how …

Generalized Detection Of Animal Behavior Using Accelerometers, Alexander J. Arrieta

Master's Theses

Animal mounted sensors are becoming increasingly used to passively monitor both domestic and wild animals. Advances in lightweight accelerometer and GPS technology have allowed many animals to be fitted with high accuracy sensors for extended periods of time. This leads to new opportunities to study animal behavior without direct observation. However, interpreting the raw data is difficult due to the high volume and missing context of the information. Machine learning techniques excel at extracting information from raw data streams and are excellent candidates for processing the sensor data. However, due to large variance in how different animals execute the same …

Bridging The Gap Between Network Science And Network Systems To Identify And Mitigate Cyber Risk: Identify And Mitigate Backdoor Attacks On Graph Neural Networks And On Complex Systems, Sabah Ettahri

Electrical & Computer Engineering Projects for D. Eng. Degree

This doctoral project aims to bridge the gap between graph theory and network science to identify and mitigate cyber risk, represented as a CY-Triangular Network that connects different networks. The CY-Triangular Framework is a cybersecurity system that integrates graph theory and network science through an interoperable learning approach. The objective of this project is to bridge the gap between two domains: network science and network systems. Accordingly, it examines one representative network from each field, focuses on a complex system network, and explores Graph Neural Networks (GNNs). The connection between these domains lies in graph theory. This research demonstrates that …

Examining The Roles Of Embodiment And Theory Of Mind In Shaping User Perceptions Of Llm-Driven Conversational Agents, Elizabeth A. Schlesener

All Dissertations

Large Language Models (LLMs) have advanced conversational agents, enabling natural, human-like interactions in domains such as education, programming, and workplace collaboration. Yet, user distrust persists over privacy, accuracy, and bias. As developers work to mitigate these issues and human-AI collaboration expands, reinforcing trust in LLM-driven systems is essential. To address this problem, this dissertation explores the role of anthropomorphic form in LLM-driven conversational agents and its impact on user perception.

According to the familiarity thesis, humans attribute human-like characteristics to nonhuman entities — a process known as anthropomorphism — to better comprehend unfamiliar phenomena, based on the assumption that they …

Ai In Consideration Of Her: Accounting For Gendered Workplace Dynamics In The Design And Evaluation Of Human-Centered Ai Integration In Everyday Workplaces, Kelsea S. Schulenberg

All Dissertations

Rapid advancements in the technical capabilities and availability of generative Artificial Intelligence (AI) systems, such as OpenAI's ChatGPT, have drawn widespread attention to the opportunities and challenges associated with AI integration into everyday workplaces (i.e., office-type work). Following calls for organizations to consider the ethical and workplace-specific impacts of generative AI's use before integrating it into the workplace, this dissertation addresses three critical gaps in Human-Centered Computing (HCC) and AI workplace integration research. First, this dissertation unpacks the underdeveloped links between women's representation - or lack thereof - in AI-related fields and how their experiences with gendered workplace dynamics in …

Application Of Graph Neural Networks On Phase Space Graphs For Cybersecurity, Parker H. Cole

Graduate Theses and Dissertations (2019 - present)

Non-linear phase space analysis may be used to represent time-series data as graph data with transitions between states in the time domain. By studying these transitions, we can predict anomalies within the system. Previous research has demonstrated success in learning from phase graphs for malware and seizure detection. These solutions either require extracting global features or converting the graph into an image for convolutional neural networks (CNNs), which adds a layer of complexity and limits the size and potential expressiveness of a graph. To sidestep current limitations, this study proposed Graph Neural Networks (GNNs) for analyzing phase graphs. GNNs do …

Algebraic Approach To Data Processing: Techniques And Applications, Julio Urenda

Open Access Theses & Dissertations

In many areas of human knowledge, symmetries and invariances play an important role. In fundamental physics, starting with Relativity Theory, new physical theories have been formulated in terms of invariances and of the corresponding transformation groups – i.e., in terms what a mathematician would call an algebraic approach. In engineering, devices like wind tunnels, which are based on scale-invariance, enable us to test smaller-scale models of the actual designs. In biological sciences, symmetries and invariances are extremely important in analyzing the shape and functioning of living beings, from mammals to viruses. Invariance and symmetry – in the form of fairness …

Multi-Hop Hybrid Graph Neural Network, James Arthur

Open Access Theses & Dissertations

Graph-structured data appear across diverse domains, such as social networks, citation graphs, biological systems, and knowledge bases. Graph Neural Networks (GNNs) have emerged as a powerful framework for learning on such data, yet existing architectures face significant challenges. Graph Convolutional Networks (GCNs) suffer from over-smoothing as depth increases, Graph Attention Networks (GATs) introduce computational and statistical instabilities, and naïve multi-hop propagation inflates memory and computation while failing to adapt to topology. These limitations motivate the development of a new framework that is both expressive and scalable. This dissertation proposes the Multi-Hop Hybrid Graph Neural Network (MHHGNN), a novel architecture that …

Microgrid Assessment And Ml-Based Power System Faults Detection Leveraging Real-Time Co-Simulation, Diego Normando Gandara Mendez

Open Access Theses & Dissertations

The rapid growth of distributed energy resources (DERs) and the increasing reliance on data-driven decision making have reshaped the operational challenges of modern electric power systems. As microgrids become more prominent in distribution networks, utilities require methods that unify planning, control, and real-time situational awareness to ensure resilient operation under faulted or uncertain conditions. The goal of this MSEE thesis is to design and validate a latency-aware ML framework for rapid, reliable fault detection in distribution grids. To achieve the goal of the thesis, there are three specific objectives. Objective 1 evaluates optimized microgrid configurations under varying DER levels and …

Lamda: A Longitudinal Android Malware Dataset For Benchmarking Concept Drift Detection And Adaptation, Md Ahsanul Haque

Open Access Theses & Dissertations

Machine learning (ML)-based malware detection systems often fail to account for the dynamic nature of real-world training and test data distributions. In practice, these distributions evolve due to frequent changes in the Android ecosystem, adversarial development of new malware families, and the continuous emergence of both benign and malicious applications. Prior studies have shown that such concept drift—distributional shifts in benign and malicious samples—leads to significant degradation in detection performance over time. Despite the practical importance of this issue, existing datasets are often outdated and limited in temporal scope, diversity of malware families, and sample scale, making them insufficient for …