Digital Commons Network^™

Train In Vain: Functionality-Preserving Poisoning To Prevent Unauthorized Use Of Code Datasets, Yuan Xiao, Yuchen Chen, Jiaming Wang, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

Research Collection School Of Computing and Information Systems

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full-dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module preserves type correctness, suppresses static-analysis warnings, and …

Hsv-1 Us3 Hijacks Conserved Actin Regulatory Complexes To Drive F-Actin Remodeling, Md Imran Hossain, Md Arifuzzaman, Md Mehedi Hasan, Seung Jong Park, Leila Rahimian, Ojasvi Dutta, Vladimir Chouljenko, Harikrishnan Mohan, Reza Ghavimi, Konstantin G. Kousoulas

Computer Science Faculty Research & Creative Works

The herpes simplex virus 1 (HSV-1) US3 is a multifunctional serine/threonine kinase that promotes HSV-1 replication and spread. But its role and the mechanisms by which US3 regulates actin cytoskeletal remodeling remain poorly defined. We combined flow cytometry, confocal microscopy, immunoprecipitation-mass spectrometry (IP-MS), protein complex mapping, and machine learning to characterize US3-mediated F-actin dynamics. Flow cytometry and confocal microscopy showed that wild-type HSV-1 induces significant F-actin remodeling, while the ΔUS3 mutant displays F-actin levels comparable to uninfected cells, identifying US3 as a key regulator. IP-MS identified 47 high-confidence US3 interactors enriched in conserved actin regulatory complexes, including Arp2/3 nucleation machinery, …

Unmasking Twitter Bots: An Applied Machine Learning Approach, Rayane El Raba’A, Layal Abu Daher

BAU Journal - Science and Technology

The rapid growth of social networks has led to increased challenges, such as fraud, cyberbullying, and the spread of automated accounts (bots). Detecting anomalies within these networks is essential to maintaining security and trust. This study explored machine learning algorithms: Random Forest, XGBoost, Support Vector Machine (SVM), and Logistic Regression for anomaly detection in social networks, specifically focusing on Twitter bot identification, By applying AI-driven data mining techniques to a dataset of 37,438 Twitter bot accounts dataset, the research evaluates the effectiveness of these models in detecting unusual patterns. XGBoost achieved the highest accuracy (84.9%), with an ROA_AUC of 0.87, …

Tumor-Immune Dynamics With Memory And Time Delay: A Fractional-Order Model With Ctla-4 Regulation, Mutaz Mohammad, Mohyeedden Sweidan, Alexander Trounev, Fathalla Rihan

All Works

This study develops a fractional-order tumor-immune interaction model incorporating Caputo memory effects, delayed immune activation, and CTLA-4 checkpoint regulation. The model describes the coupled dynamics of tumor cells, CD4^+ T cells, IFN-γ, and CTLA-4, and extends classical integer-order tumor-immune models by accounting for hereditary immune responses and biologically motivated latency effects. Theoretical properties, including positivity, boundedness, equilibrium structure, and fractional-order stability, are examined to establish the biological and mathematical consistency of the model. The delayed fractional system is then investigated computationally by comparing several numerical methods, including finite difference discretization, Daubechies wavelet collocation, Euler wavelet collocation, and a predictor-corrector scheme. …

Interval-Valued Neutrosophic Dombi Bonferroni Mean Aggregation Operators In Medical Diagnosis And Sustainable Energy, Maryam Faisal, Muhammad Nadeem, Muhammad Kamran

Neutrosophic Systems with Applications

Medical diagnosis is one of the most difficult fields in which decisions must be made due to the fact that medical information often has characteristics of uncertainty, incompleteness, imprecision and even contradiction. Traditional aggregation and decision-making methods are often not well suited to such complexities, and may result in less reliable diagnostic outcomes. In order to overcome these drawbacks, the authors propose a new approach using a novel representation of Interval-Valued Neutrosophic Sets (IVNSs), the Dombi operational laws, and Bonferroni Mean (BM) aggregation operators. The proposed framework is specifically aimed at coping with uncertainty, indeterminacy and falsity all at once …

Operationalizing Supply-Chain Hygiene In Graduate Is Education: A Hands-On Module For Secure Software And Ai/Ml Pipelines, Dominic A. Wilson

Journal of Cybersecurity Education, Research and Practice

Supply-chain attacks (including typosquatting, dependency confusion, compromised builds, dataset poisoning, and backdoored models) pose growing threats to analytics platforms central to Information Systems (IS). While frameworks like the Secure Software Development Framework (SSDF) and Supply-chain Levels for Software Artifacts (SLSA) offer guidance, IS curricula often lack accessible, infrastructure-light modules that build practical skills for mitigating these risks. This experience report presents a two-week module embedded in a graduate Secure Coding course required for a Master’s in Applied Security and Analytics degree. The module operationalizes secure development habits across both traditional software and machine learning (ML) pipelines. The module addresses a …

Parametric Modular Answer Set Programs Made Declarative, Jorge Fandinno, Yuliya Lierler, Torsten Schaub

Computer Science Faculty Publications

In this paper, we explore the concept of modularity in first-order answer set programming (ASP). We introduce a new formalism called parametric modular logic programs, which allows defining subprograms with parameters and intensionality statements. We demonstrate how this formalism can capture the semantics of clingo-programs with collective control , a feature that enables structuring and instantiating subprograms. We provide theoretical foundations for modular ASP, illustrate its usefulness, and connect to traditional non-modular ASP.

Autoencoders As Classifiers Trained On Single Sources Of Radiographic Images For Generalizability Across Unseen Sources, Ryan M. Putney

USF Tampa Graduate Theses and Dissertations

Artificial neural networks trained to classify X-ray images according to disease state will learn to distinguish between technical or procedural variations in the images rather than features relevant to the disease. For example, the model might learn to recognize the machine that captured the image or to distinguish an image taken while the patient is lying supine or standing upright. The present work is aimed at using autoencoders as a generalizable classifier to detect COVID vs pneumonia (PNA) X-ray images. The first experiment was to find an architecture for a fully convolutional autoencoder (CAE) and for a convolutional autoencoder with …

The Impact Of Gender Sensitization On Requirements Elicitation: A Controlled Experiment, Ruthbertha Kateule, Salome Maro, Leonard Peter Binamungu

Tanzania Journal of Engineering and Technology (TJET)

Previous studies in software engineering have reported the importance of considering gender aspects in various software engineering activities, including requirements engineering, however, to the best of our knowledge, no work has investigated the impact of gender sensitisation on eliciting gender inclusive software requirements. The objective of this study was to understand the impact of gender sensitisation on software requirements elicitation. We conducted a controlled experiment using 40 undergraduate students from three different computing programs at the University of Dar es Salaam. The 40 participants were divided into 9 groups with both males and females. The participants were asked to elicit …

Trustworthy Reinforcement Learning And Communication-Efficient Multi-Agent Systems, Rui Zuo

Dissertations - ALL

The rapid proliferation of autonomous systems, such as Unmanned Aircraft Systems (UAS) transitioning to large-scale Beyond Visual Line of Sight (BVLOS) operations, demands a paradigm shift toward reliable, transparent, and resilient autonomy. While Deep Reinforcement Learning (DRL) and Multi-Agent Reinforcement Learning (MARL) have demonstrated exceptional capabilities in complex decision-making and coordination, their real-world deployment in safety-critical domains is hindered by two fundamental challenges. First, the opaque, "black-box" nature of DRL models prevents human operators from understanding and trusting the agents' underlying logic. Second, as multi-agent operations scale, they become severely constrained by the stochastic link qualities and strict bandwidth limitations …

From Detection To Segmentation: A Foundation Model Approach To Organoid Brightfield Image Analysis Using Sam 3, Hiren Manani

Theses - ALL

This thesis presents the first systematic application of SAM 3, a unified foundation model for promptable segmentation, to mouse small intestinal organoid brightfield microscopy image analysis. The work spans the complete pipeline from zero-shot baseline evaluation through domain-specific fine-tuning on a GPU cluster, and documents the full engineering process required to adapt a state-of-the-art foundation model to a novel biomedical imaging domain. A comprehensive literature review of over 20 papers spanning detection-based, classical segmentation, foundation model, and morphological analysis approaches identified a clear research gap that this thesis addresses. Five critical compatibility patches were developed to deploy SAM 3 on …

Constrained Neural Intelligence: Investigations Into Deep Multi-Objective Optimization, Naveed Tahir

Dissertations - ALL

Neural intelligence is identified with complex learning problems optimized over the high-dimensional, non-convex parameter spaces of deep neural networks. Solving such problems generally requires handling competing objectives and conflicting constraints. This is traditionally dealt with using heuristic methods that collapse such complexity into unconstrained, singular objectives. While computationally convenient, this invites a tradeoff against the precision and stability afforded by non-heuristic, geometry-aware approaches. This dissertation explores constrained multi-objective learning in various applied and theoretical contexts and highlights the feasibility of approximate methods as well as the necessity of exact methods. We propose a framework for equality-constrained deep learning via approximate …

Multi-Modal Survival Prediction On Breast Cancer Mammograms And Enabling Multi-Institutional Collaborations With Federated Learning, Nikolas Koutsoubis

USF Tampa Graduate Theses and Dissertations

Cancer remains one of the leading causes of mortality worldwide, and machine learning is well positioned to leverage the large volumes of routinely collected clinical and imaging data to improve patient outcomes. Realizing this potential at scale requires three capabilities that current practice does not yet deliver in combination: models that integrate the multiple data modalities clinicians use, training procedures that respect institutional data-sharing constraints, and tooling that enables sharing of de-identified data when federated approaches are not sufficient. This dissertation develops methods and infrastructure addressing each of these capabilities in the context of breast cancer and oncology more broadly. …

Algorithmic Monocultures In Hiring, Rishi Bommasani, Sarah H. Bana, Kathleen A. Creel, Dan Saul Jurafsky, Percy Liang

Economics Faculty Articles and Research

Many employers screen job applicants with algorithms built by the same few algorithm vendors. We hypothesize that algorithmic monoculture leads to the same individuals and members of the same racial groups facing rejection. We acquire and analyze a novel dataset of 3 million applicants submitting 4 million applications where all the applications are screened by algorithms built by the same vendor. We find clear racial disparities in applicant outcomes. Of all applications submitted by Asian and Black applicants, 14.74% and 25.87% are submitted to positions that adversely impact Asian and Black applicants, respectively, according to U.S. employment discrimination standards. Individuals …

Research On Optimization Modeling Method For Eye Tracking In Solfeggio Cognitive Simulation, Kun Zhang, Jiajie Qian, Shuhong Ma, Zengxu Zhao, Yuchen Pan, Yaoqi Tang

Journal of System Simulation

To address the fixation offset problem caused by head movement in music solfeggio teaching simulation and the lack of system-level simulation validation in existing methods, this paper proposed a fixation accuracy optimization method integrating image semantic understanding, temporal trajectory modeling, and solfeggio cognitive simulation. With Vision Transformer as the core, after preprocessing via Mahalanobis distance, sliding window, and region of interest, position offset perception, offset residual regression, and dual-pathway fusion were introduced to achieve offset modeling and correction under unlabeled conditions. Simulation results indicate that the error of this method decreases by 43.9% compared with the original value error; removing …

Building Trustworthy Information Systems: A Unified Framework For Comparative Risk Detection, Parisa Momeni

USF Tampa Graduate Theses and Dissertations

Risk detection in large scale information systems increasingly depends on heterogeneous data generatedby both centralized and distributed ecosystems. While centralized systems provide curated and validated reports, distributed environments produce large-scale and real-time observational evidence. Existing computational approaches analyze these ecosystems in isolation, limiting systematic comparison of risk repre-sentations across heterogeneous sources.

This dissertation presents a unified computational framework for comparative risk detection across centralized and distributed information systems. The framework provides a domain independent methodology for transforming heterogeneous risk reporting data into comparable multidimensional representations. To enable interpretable comparison of heterogeneous risk distributions, this work introduces the Geometric Overlap Score …

Seeing Around Corners: An Indirect Light Transport Decomposition Framework For Fusing Physics And Learned Priors, Fadlullah Raji

USF Tampa Graduate Theses and Dissertations

Non-line-of-sight (NLOS) imaging, or seeing around corners, is the ability to recover information about objects hidden from direct view and remains one of the most compelling challenges in computational imaging. Existing approaches fall broadly into two categories: active and passive. Active time-resolved methods achieve impressive performance but require specialized pulsed laser hardware and ultrafast detectors, making them expensive and limited by slow measurement acquisition. Passive NLOS methods, which instead exploit the subtle soft shadows (penumbrae) cast by a hidden scene onto a visible matte surface, have recently emerged as a practical alternative. However, existing passive approaches are largely limited to …

Non-Euclidean Geometries And Fairness Constraints In Advanced Clustering, Arnab Seal

Master’s Dissertations

A fundamental challenge in modern unsupervised learning is adapting classical clustering algorithms to handle complex, real-world data constraints. Traditional models often assume data resides in a flat, Euclidean space and optimize strictly for cluster cohesion, thereby failing to capture intrinsic hierarchical structures and ignoring sociotechnical demographic biases. This thesis addresses these critical limitations by extending generalized mean-shift dynamics into two novel clustering frameworks. First, to natively accommodate data with tree-like structures (e.g., taxonomies and social networks), we propose Hyperbolic Gaussian Blurring Mean Shift (HypeGBMS). By projecting data into the Poincar´e ball model and utilizing M¨obius vector space operations, HypeGBMS successfully …

Leveraging Spatial Statistics For Domain Adaptation Of Vision Language Models In Medical Vqa, Himanshu Raj

Master’s Dissertations

Recent advances in Vision–Language Models (VLMs) have demonstrated strong performance in Medical Visual Question Answering (Medical VQA) task. Although they perform very well within their domains, these models often experience issues with their generalization ability on unknown clinical distribution data because of different imaging technologies and patient groups used in various medical facilities. Generalization problems faced by these models make their practical application in the field of VLM-based medical VQA systems rather difficult. To overcome this limitation we proposed our method named Spatial Semantics Aware Domain Adaptation (SSADA), which is an integrated framework that combines both finetuning and prompt-based in-context …

To What Extent Could Quantum Computing Pose A Threat To Global Modern Data Security?, Aniket Maheshwari

Journal of Cybersecurity Education, Research and Practice

Quantum computing has emerged as a transformative technology with the potential to fundamentally disrupt modern cryptographic systems that underpin global data security. This paper examines the extent to which quantum computing could pose a threat to modern global data security by synthesising existing technical, institutional, and policy-oriented literature. Drawing on a narrative review of scholarly research, industry reports, and government frameworks, the analysis focuses on the implications of quantum algorithms such as Shor’s and Grover’s, which challenge the mathematical foundations of widely used cryptographic schemes. The findings suggest that while quantum computing presents a credible long-term threat to asymmetric encryption …

Label-Flip Attack Detection Via Trust-Weighted Aggregation In Federated Learning For Underground Mine Security, Md Sazedur Rahman, Sanjay Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

Underground mining operations are increasingly dependent on autonomous vehicles, robotic drilling systems, and intelligent inspection platforms operating in confined, GPS-denied tunnel environments. These systems rely on distributed perception models to interpret navigation cues, hazard warnings, and environmental signals in real time. While centralized deep learning can enhance model performance, transferring raw operational data across mining sites introduces serious confidentiality and security risks. Federated Learning (FL) offers a privacy-preserving alternative by enabling collaborative model training without sharing local datasets. However, deploying FL in underground mining introduces several critical challenges: (i) Training labels may be modified either maliciously by compromised clients or …

American Sign Language Recognition And Analysis Using Deep Learning, Saurabh Kumar Soni

Master’s Dissertations

In this work I build a system that recognizes isolated American Sign Language (ASL) words, and I use it to ask one fairly direct question: when training data is scarce, is it better to look at the video pixels or at the geometry of the signer’s body? To find out, I train two very different models on exactly the same clips. The first is appearance-based. Every frame is run through standard preprocessing and a ResNet50 backbone pre-trained on ImageNet, which turns it into a 2048-dimensional feature vector, and a Bidirectional LSTM then reads that sequence over time. The second model …

Enhanced Embedding For Multimodal Medical Visual Question And Answering, Akash Suna

Master’s Dissertations

Visual Answering of questions in the field of Medical which is called as (VqA) has grown as a dominant area of research that fuse processing of natural language and vision of computer often known as CV or NLP to assist in medical decision-making. However, effective multimodal fusion between medical images and clinical questions remains a significant challenge. This thesis examines the application of the Perceiver IO architecture as an efficient multimodal aggregator for medical VQA. The work has been carried out in multiple directions. First, a classification-based framework is developed by combining Vision Transformer (ViT) and ClinicalBERT alongside a Perceiver …

An Empirical Study Of Rlvr Fine-Tuning For Mathematical Problem Solving In Llms, Rashmi Konnur

Master’s Dissertations

Large language models have shown immense improvement in coding and math performances thanks to reinforcement learning boosted algorithms. However, its true impact on broadening the reasoning and analytical capacities of an LLM is still contended. In this dissertation, we outline the foundations of Large Language Models, and delve into Reinforcement Learning with Verifiable Rewards (RLVR). We discuss various strategies to efficiently manipulate memory during a fine tuning update. We finally perform RLVR fine-tuning techniques on different models with varied use cases and compare their performances, which corroborate the efficiency of RLVR.

Efficient Multimodal Foundation Model Tuning For Hallucination Mitigation, Fei Zhao

ETDs from 2020-2029

Over the past few years, multimodal foundation models have achieved remarkable progress in perception and understanding. However, two challenges limit their reliability: (1) dependence on offline training, which in most real-world settings requires large volumes of labeled data and, as a result, hinders the model’s ability to adapt to new data or domains; (2) weak cross-modal grounding, which often leads to hallucinated content generation, producing descriptions that are linguistically fluent but inconsistent with the input visual evidence. This dissertation frames hallucination mitigation as an outcome of transitioning from fixed learning (static, offline fine-tuning) to adaptive, feedback-driven lifelong learning. By incorporating …

Learnable Structured Attention For Student-Aware Knowledge Distillation In Dense Prediction, Chen Liu

ETDs from 2020-2029

Dense prediction tasks, including object detection and semantic segmentation, require models to produce structured predictions and are widely used in real-world vision applications. Although deep networks have achieved strong performance on these tasks, their high computational cost limits deployment on resource-constrained systems such as autonomous-driving vehicles. Knowledge distillation (KD) addresses this issue by transferring knowledge from a large teacher model to a compact student model. However, existing distillation methods for dense prediction face greater challenges than those for classification due to the more complex task requirements. To overcome the challenges, this thesis presents a unified study of adaptive distillation for …

Modeling And Mitigating Stale Hardcoded Secrets In Version Control History, Katarina Valentine Capalbo

USF Tampa Graduate Theses and Dissertations

Hardcoded secret vulnerabilities remain a growing and persistent problem that can be difficult to mitigate once exposed. While there has been significant research and advancements in identifying and preventing hardcoded secrets, less attention has been given to understanding the risks of leaving these secrets behind in version control history, as well as analyzing the sanitization of hardcoded secrets. These challenges present a growing gap between the risk and ability to mitigate and sanitize existing secret exposures. This thesis begins to address this gap by formalizing a threat model for hardcoded secrets that persist in Git version control history after the …

Kernelizing Protein Interaction Languages: Spectral Approximations And Random Fourier Features, Aishik Ghosh

Master’s Dissertations

Protein-peptide interactions play an important role in many biological phenomena, spanning adaptive immunity to disease pathology. In the Sliding Window Interaction Grammar (SWING) framework, interactions are represented as sequences of biochemical tokens embedded using Doc2Vec, allowing robust generalisation to unobserved MHC alleles. However, classification remains limited to a single Euclidean feature space that is incapable of resolving binding landscapes. This dissertation develops SWING for four distinct kernel types: Gaussian, Laplacian, anisotropic (ARD), and the Spectral Mixture (SM) kernel, each approximated using scalable Random Fourier Features. The SM kernel incorporates prior knowledge about secondary structure into its spectral density as biological …

Learning In Infants Using Intrinsically Motivated Goal Conditioned Reinforcement Learning, T I Darsan

Master’s Dissertations

Traditional artificial intelligence models learn by passively digesting large datasets. In contrast, human infants discover skills by actively interacting with their bodies and environments without explicit external rewards. This thesis introduces the Composer Architecture, a machine learning framework designed to mimic this autonomous, open-ended development. The Composer architecture operates in a multi-stage loop, the latent model using Contrastive Learning Through Time (CLTT) to compress high-dimensional raw data from visual, proprioceptive, and touch sensors into a low-dimensional space. To preserve data relationships and prevent topological collapse, a Softmax activation forces these latent representations to lie smoothly on a probability simplex. A …

Design And Evaluation Of A Code-Switching-Aware Multilingual Conversational Ai System Using Advanced Rag Architectures, Ashutosh Juvale

Master’s Dissertations

Conversational artificial intelligence has become the primary interface through which hundreds of millions of users in India seek information and customer support. Yet the way these users actually write and speak is fundamentally at odds with the monolingual assumptions baked into most retrieval and generation systems: they code-switch, fluidly mixing one or more of the twenty-two scheduled languages of India with English, frequently typing Indic words in the Roman script ("mera refund kab tak aayega"). Standard Retrieval-Augmented Generation (RAG) pipelines silently fail on such input — the retriever returns off-topic passages because the query and the knowledge base live in …