Digital Commons Network^™

Synthetic Malware Generation Using Generative Ai, Phanidhar Sai Sravan Chandana

Master's Projects

Malware grows in numbers and complexity, evading conventional signature-and anomaly-based defenses and worsening extreme data sparsity and class imbalance problems for machine learning based detection. Generative models, specifically GANs conditioned on contextual embeddings like BERT have proved effective augmenting training corpora to improve classifier accuracy, but these approaches have largely produced family-specific samples In this paper, we propose a generalized augmentation scheme for generating robust malware embeddings for various families. We begin by extracting opcode sequences from 13 malware families and encoding them into three embedding methods: CountVectorizer, TF-IDF, and BERT’s ‘[CLS]‘ vectors. We therefore train standard GANs and Wasserstein …

Malware Opcode Embedding And Quality Assessment Of Generative Sample Embeddings, Atishay Jain

Master's Projects

Malware is software used to damage and disrupt computer systems with the intent to cause damage to the victim. Malware detection and classification into malware families is a crucial problem for cybersecurity researchers. One of the major bottlenecks in improving these systems is the shortage of good quality labeled malware data, especially for malware families with scarce samples. Researchers have utilized generative models to generate malware data to address this issue. Malware embeddings encode patterns within a malware file, which can be used to detect and classify malware. Recently, encouraging results have been obtained in generating malware embeddings using generative …

Malware Generation And Classification Using Pixelcnn, Mounika Krishna Teja Karumudi

Master's Projects

Malware poses a serious threat to both data privacy and system security. With the wide variety of malware families and the surge in cyber-attacks, the accurate classification of malware is crucial for building effective detection and prevention systems. In recent years, deep learning (DL) methods in computer vision have shown promise in classifying malware by converting malware files into visual representations and applying DL algorithms to classify the resulting images. Among the different approaches to malware family classification, image-based methods have gained significant interest. This research focuses on leveraging DL techniques for image-based classification of malware. The success of identifying …

Enhancing Robustness Of Cnn Model For Malware Detection Using Gan-Based Data Augmentation And Transfer Learning, Milind Anand Pathak

Master's Projects

Malware classification is a critical component in the field of cybersecurity. Accurate identification of a malware family can enable timely threat detection and response. In this thesis, we propose a robust image-based malware classification pipeline using Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), with a focus on improving performance for underrepresented malware families. We train a baseline CNN model on the Malimg dataset across 25 malware families, but observe misclassifications in classes with limited data and overlapping visual features. To address this, we apply targeted augmentations and generate class-specific synthetic data using StyleGAN2-ADA. A CNN trained on the …

Maple: Malware Analysis Through Projection Of Low-Dimensional Embeddings, Quang Duy Tran

Master's Projects

Machine learning has become a popular and powerful tool for malware analysis and detection. With the rise in popularity of natural language processing (NLP) techniques, researchers can now extract contextual embeddings from malware opcode sequences, enabling the capability to analyze hidden malware patterns and advanced code obfuscation strategies. However, unlike malware binaries, which can be directly visualized as images, these embeddings exist in high-dimensional spaces, making it difficult to observe their global patterns or spatial structures. In this paper, we propose a framework for visualizing malware embeddings in lower-dimensional space using various dimensionality reduction techniques. Our approach converts malware binaries …

Comparative Analysis Of Adversarial Permeability In Cpu-Native, Qat And Onnx-Based Quantized Transformer Models, Fahad Siddiqui

Master's Projects

This work explores securing and optimization of Transformer-based time series forecasting models. We employ several quantization techniques, including quantization-aware training (QAT), and tested the robustness of quantized models by adversarially attacking them. The preliminary results of this work, in our controlled setup, indicate that quantized models outperform the full precision model in terms of robustness against adversarial attacks. They achieved this robustness while showing a very minimal decrease in their forecasting performance.

Human Vs. Llm: Interpreting Emotion From Neutral Faces In Contextually Charged Backgrounds, Sai Mounika Peteti

Master's Projects

In this study, we investigate the intersection of cultural context, visual perception, and implicit bias in interpreting neutral human expressions. Specifically, we explore how emotionally charged backgrounds can shape viewers interpretations of neutral facial expressions. Using an experimental setup, participants are shown neutral human portraits paired with varying background types ranging from emotionally neutral or pleasant to evocative scenes. Participants are tasked with selecting which background best matches the emotional state of the person depicted in the portraits. Eye-tracking data is collected to analyze visual attention patterns and cognitive processing. In parallel, we also evaluate how large language models (LLMs) …

Clustering Organ Cell Types, Venkata Satya Swathi Mattaparthi

Master's Projects

The Human Cell Atlas (HCA) created a reference map of all human cells. My project uses the Tabula Sapiens dataset, developed under HCA and based on single-cell RNA sequencing data, to explore cell type and tissue diversity. I performed experiments using the Elbow method and a formula based on dataset observations to determine the number of clusters, then applied k-means clustering on two representative subsets of the All Cells dataset. Clusters were selected for analysis using Shannon’s Diversity Index and Pielou’s Evenness. A novel algorithm based on the cell differentiation tree was used to validate the biological coherence of the …

Large Language Models For Bacterial Genomic Analysis, Manvendra Chavan

Master's Projects

Identification of bacterial gene sequences with agricultural applications has the potential to transform agricultural biotechnology. These genes can be used in environmentally friendly pest control strategies. One such use case is identifying genes with potential insecticidal properties. With an increasing number of genomic information and decreasing numbers of available annotated sequences, finding new insecticidal genes has become more challenging.The traditional methods relying on sequence alignment and annotated databases are not effective in detecting functionally relevant genes lacking close homology to known cases. This project investigates the data-driven classification of genes by sequence modeling. This research is focused on learning DNA …

Strengthening The Preservation Ecosystem For Below-Market-Rate Housing In Santa Cruz, Bennett Williamson

Master's Projects

In Santa Cruz, California, policies and political movements of the last fifty years have both prevented sprawl and stymied the construction of new infill housing. As a result, today Santa Cruz is one of the most expensive housing markets in the nation, and the lack of available affordable housing has led to incredibly high rent burdens for the majority of the population, putting residents at risk of displacement through landlord action or market forces. This report assesses the efficacy of preserving existing affordable housing as an anti-displacement strategy in Santa Cruz. It uses key stakeholder interviews with local housing practitioners …

Genegate: Genetic Gating In A Mixture-Of-Experts For Real-Time Multi-Objective Traffic Signal Control, Rashmi Vishwanath Bhat

Master's Projects

Urban traffic signal control often needs to juggle between competing goals. It needs to minimize delays, reduce emissions, prevent crashes, and prioritize emergency vehicles all while the demand is constantly fluctuating. Traditional fixed-time or statically blended policies cannot reallocate priorities quickly when conditions change. We introduce GeneGate, a mixture-of-experts framework that uses a lightweight genetic gate to fuse four specialist controllers (throughput, emissions, safety, emergency) and adjusts their weights in real time. A short offline genetic search produces a robust initial blend, and an online micro-evolution step refines it every few cycles based on live traffic feedback. GeneGate’s adaptive gating …

Nontraditional Students Enrolling In Online Education: Assessing Outcomes And Barriers To Success, Kua Vang

Master's Projects

Online education has significantly reshaped how colleges and universities define and evaluate academic achievement. In March 2020 during the height of the Covid-19 pandemic, the U.S. government enforced social distancing regulations that affected operational continuity for higher education institutions. The need to transition from traditional classroom instruction to online was unavoidable. Institutions were not prepared, however, and their shortcomings in providing high-quality online learning for students were exposed. The inadequacy can be due to higher education institutions decade-long mindset of seeing online education as a less credible alternative. As a result, institutions are more eager than ever before to invest …

Collaborative Governance In Practice: Evaluating Intergovernmental Relations Through The Santa Clara County Healthy Cities Initiative, Astrid J. Robles

Master's Projects

In the United States, intergovernmental relations (IGR) is rooted in the principles of American federalism, which focuses on the constitutional power dynamics between national, state, and local governments. While federalism outlines the structural framework, IGR specifically focuses on how federal, state, and local governments interact administratively, financially, and politically within the federal system. Beginning in the 1960’s, governments across the U.S. began to rely on non-governmental and private sector organizations for program implementation (Boyd & Fauntroy, 2000). This shift gave rise to the concept of collaborative governance, which expanded the scope of IGR by incorporating traditionally excluded groups from the …

Advanced Knowledge Extraction With Biomedical Data Using Llms, Akshat Krishna

Master's Projects

The rapid growth of biomedical research has led to an overwhelming volume of unstructured textual data in the scientific literature. This has necessitated the development of an automated approach for knowledge extraction and integration. In

this project, we present a comprehensive pipeline for constructing a unified biomed- ical knowledge graph by combining two well-known datasets: CHEMPROT [1],

which captures chemical–protein interactions, and EU-ADR [2], which annotates drug–gene–disease relationships. In order to identify important biomedical entities and interactions from CHEMPROT dataset, we perform Named Entity Recognition (NER) and relation Extraction (RE) using state-of-the-art biomedical models like BioBERT [3], BioGPT [4] and …

Why We Need To Fill In Our Mixed-Use Communities’ Business Vacancies And How We Can Do That, Victor Huynh

Master's Projects

This planning report provides an in-depth exploration as to why so many mixed use communities, including transit-oriented developments, in metropolitan regions across the country are facing challenges with filling in their retail business vacancies at the ground floor. It also provides a current snapshot of best practices to remedy this widespread barrier to cities functioning more effectively and sustainably. This report provides a combination of findings from a literature review which identifies the most common reasons and remedies for business vacancies, and a research design which identifies which urban planning or urban design characteristics correlate most frequently with case sites …

Enhancing Code Review Automation With Large Language Models Using Qlora Fine-Tuning And Rags, Sumukh Naveen Aradhya

Master's Projects

In this technological era where Artificial Intelligence and Machine Learning are revolutionizing various domains, Large Language Models (LLMs) are emerging as a very powerful tool. In the software development lifecycle, it is extremely important to have reliable code reviews to ensure security and maintain code quality. This project aims to survey various existing methodologies to aid creation of efficient code review automation agents and also research on ways to make this process more efficient. Parameter Efficient Fine-Tuning (PEFT) methodologies such as LoRA and QLoRA have been explored with an additional focus on a hybrid model that combines adaptive QLoRA with …

Equity In Public Budgeting: Community Engagement In Morgan Hill, Ariana Perez

Master's Projects

Through this research, I will examine what citizen participation strategies have been implemented and their role and effectiveness in addressing wealth inequities. My research will explore these topics and examine what programs and policies the City of Morgan Hill can implement to increase residents' sense of belonging and ultimately push for greater social equity. My primary research question is, what are the programs and policies that the City of Morgan Hill can implement to engage immigrant communities, specifically Spanish-speaking residents, and low-income residents in shaping decisions around public investments and funding? This project will serve as a needs assessment to …

Characterizing Somatic Variants In Nanopore Data With Machine Learning, Shwethal Sayeeram Trikannad

Master's Projects

Oxford Nanopore Technology (ONT) is a popular long-read sequencer in genomics. However, its high base-calling error rate produces several sequencing artifacts. Detection of somatic variants in ONT sequenced tumor-normal samples remains challenging due to low frequencies. In this study, machine learning was applied to a dataset created by benchmarking ClairS output against HCC1395 and colo829 truth sets to classify variants and artifacts. Relevant features were engineered from sequence context and variant site characteristics to model artifact profiles. HistGradientBoostingClassifier achieved 0.876950 accuracy, outperforming all other models. Variant quality was the top predictor with an aggregate accuracy of over 85%. This work …

Monitoring Plastic Pollution Using Bioindicators: A Global Review And Recommendations For Marine Environments, Matthew S. Savoca, Neil Angelo Abreo, Andres H. Arias, Laura Baes, Matteo Baini, Elisa Bergami, Susanne Brander, C. Anela Choy, Illaria Corsi, Bavo De Witte, Camila Domit, Sarah Dudas, Emily M. Duncan, Claudia E. Fernández, Maria Cristina Fossi, Ostin Garcés-Ordóñez, Brendan J. Godley, Daniel Gonzalez-Parades, Victoria González Carman, Bonnie M. Hamilton, Britta Denise Hardesty, Sang Hee Hong, Shirel Kahane-Rapport, Lauren M. Kashiwabara, Mariana Baptista Lacerda, Guillermo Luna-Jorquera, Clara Manno, Sarah E. Nelms, Cristina Panti, Diego J. Pérez-Venegas, Christopher K. Pham, Jennifer F. Provencher, Sara Purca, Harunur Rashid, Yasmina Rodríguez, Conrad Sparks, Chengjun Sun, Martin Thiel, Catherine Tsangaris, Robson G. Santos

Biological Sciences Faculty Publications

Monitoring the movement of plastic into marine food webs is central to understanding and mitigating the plastic pollution crisis. Bioindicators have been a component of the environmental monitoring toolkit for decades, but how, where, and which bioindicators are used in long-term monitoring programs has not yet been assessed. Moreover, these programs have yet to be synthesized and evaluated globally. Doing so is imperative if we are to learn from these pioneering programs and expand on their efforts. We reviewed global monitoring programs using bioindicators that focus on plastic pollution and found 11 worldwide that met our definition of long-term monitoring. …

Frozen Green Leaves As Potential Nutrient Subsidies In North American Mangrove Ecosystems, Katelyn Overstreet, Emily M. Dangremond, Ilka C. Feller

Biological Sciences Faculty Publications

Avicennia germinans, the black mangrove, has shifted its range limit northward, and increased in abundance in the Southeastern United States. In January 2018, a 3-day freeze event caused substantial defoliation of green leaves in A. germinans near its northernmost range limit in St. Augustine, FL. During their recovery, plants that lost their leaves grew similarly to plants fertilized with nitrogen, leading to the hypothesis that freeze-killed green leaves (frozen green) may have acted as a fertilizer. To assess the value of frozen green litter as a nutrient subsidy, we performed an experiment in which A. germinans seedlings were grown …

Edge Effects Impact Blue Carbon Dynamics Across Coastal Ecotones In A Tropical Seascape, Erik S. Yando, Jahson B. Alemu I, Kiah Eng Lim, Taylor M. Sloey, Michiel Van Breugel, Natasha Bhatia, Daniel A. Friess

Biological Sciences Faculty Publications

Coastal wetlands are important for their ability to regulate global climate through the sequestration and long-term storage of carbon. Accurate quantification of ecosystem-specific carbon dynamics (including sequestration, storage, and fluxes) is needed to develop accurate carbon budgets that inform climate change mitigation. Most work to quantify carbon dynamics either use subsampling in core habitats or benefit transfers to upscale values. While these approaches are valuable, our understanding of carbon dynamics across ecosystem transitions and overall heterogeneity remains a critical gap in coastal ecosystems as boundaries are not always clear. In this study, we established transects across both mangrove and seagrass …

Caveolin-Mediated Endocytosis: Bacterial Pathogen Exploitation And Host-Pathogen Interaction, Dibyasri Barman, Rishi Drolia

Biological Sciences Faculty Publications

Within mammalian cells, diverse endocytic mechanisms, including phagocytosis, pinocytosis, and receptor-mediated endocytosis, serve as gateways exploited by many bacterial pathogens and toxins. Among these, caveolae-mediated endocytosis is characterized by lipid-rich caveolae and dimeric caveolin proteins. Caveolae are specialized microdomains on cell surfaces that impact cell signaling. Caveolin proteins facilitate the creation of caveolae and have three members in vertebrates: caveolin-1, caveolin-2, and caveolin-3. Many bacterial pathogens hijack caveolin machinery to invade host cells. For example, the Gram-positive facultative model intracellular bacterial pathogen Listeria monocytogenes exploits caveolin-mediated endocytosis for efficient cellular entry, translocation across the intestinal barrier, and cell–cell spread. Caveolin …

Zika Virus Modulates Arthropod Histone Methylation For Its Survival In Mosquito Cells, Telvin Harrell

Biological Sciences Faculty Publications

Zika virus (ZIKV) is a mosquito-borne human pathogen that causes mild febrile illness in adults and severe neurological complications and microcephaly in newborns. Studies have reported that ZIKV modulates methylation of human and viral RNA critical for its replication in vertebrate cells. In this study, we show that ZIKV modulates mosquito S-adenosyl methionine (SAMe)-synthase, an enzyme involved in the production of SAMe (methyl donor), and histone methylation for its survival in mosquito cells. Reverse transcription quantitative PCR followed by immunoblotting analysis showed increased amounts of SAMe synthase at both RNA and protein levels, respectively, in C6/36 mosquito cells infected with …

First Reference Genomes For Two Mesophotic Reef Building Coral Species: Leptoseris Cf. Scabra And Montipora Cf. Grisea, Veronica Z. Radice, Johanna C. Gijsbers, Silvia Vimercati, Daniel J. Barshis

Biological Sciences Faculty Publications

Coral mortality is occurring worldwide at an alarming rate. Despite the immense and underestimated biodiversity of reef-building corals, very few genomes are available. Further, almost all genomic resources originate from shallow water corals even though photosynthetic, symbiotic corals occur at mesophotic depths deeper than 30 m and even >100 m. We present annotated, de novo genomes for two mesophotic, scleractinian (reef-building) corals Montipora cf. grisea and Leptoseris cf. scabra from American Sāmoa, the latter being the first genome for the widespread genus Leptoseris. We used PacBio continuous long reads and Omni-C data to assemble chromosome-level reference genomes. For Montipora …

Validating A Novel Capability Of Assessing Pathways Of Animal Water Gain And Loss, Zachary T. Steele, Karen Caceres, Zachary A. David, Lisa M. Shollenberger, Alexander R. Gerson, Seth D. Newsome, John P. Whiteman

Biological Sciences Faculty Publications

Understanding variations in the routes by which wild animals gain and lose water is challenging, and common methods require longitudinal sampling, which can be prohibitive. However, a new approach uses Δ′¹⁷O_BW (Δ′¹⁷O of animal body water), calculated from measurements of δ′¹⁷O and δ′¹⁸O in a single sample, as a natural tracer of water flux. Δ′¹⁷O_BW is promising, but its relationship to organismal variables such as metabolic rate and water intake have not been validated. Here, we continuously measured oxygen influxes and effluxes of captive deer mice (Peromyscus maniculatus), and manipulated their water intake and metabolic rate. We used …

Heterotrophy Of Particulate Organic Matter Subsidies Contributes To Divergent Bleaching Responses In Tropical Sclaractinian Corals, Connor R. Love, Kelly E. Speare, Michael D. Fox, Veronica Z. Radice, Kelton W. Mcmahon, Gretchen E. Hofmann,, David L. Valentine, Marie E. Strader

Biological Sciences Faculty Publications

Heterotrophic feeding on plankton and particulate organic matter (POM) by tropical Scleractinian corals is known to aid in the resistance and recovery from thermally induced bleaching. However, the relative importance of heterotrophy in promoting bleaching resistance and recovery is likely to vary based on ecological context and the severity of heat stress. In 2019, the Pacific Island of Mo'orea experienced mass coral mortality during a widespread marine heatwave. Many Acropora hyacinthus colonies on the shallow reef slope (5 m) were resistant to bleaching, while colonies on the deeper fore reef (14 m) often bleached and subsequently recovered, despite similar thermal …

Schistosoma Mansoni Infection Causes Consistent Changes To The Fecal Bacterial Microbiota Of Mice Across And Within Sites, Mariam A. Mhanna, David T. Gauthier, Lisa M. Shollenberger

Biological Sciences Faculty Publications

Eggs of Schistosoma mansoni are produced by adult female worms in mesenteries of infected hosts. Eggs can cross the intestinal barrier and form granulomas in the tissue or breach and exit the host through fecal excretion. These interactions may affect the host microbiome assemblages. Given the potential for schistosomal alteration of host gut microbiome and subsequent effects on the fecal bacterial composition, it is important to conduct controlled microbiome studies on model animals. While pursuing these studies, it is important to take into account the different conditions in which microbiome studies are conducted and their consequent impacts on variability and …

Addressing The Productivity-Susceptibility Analysis In Data-Limited Fisheries For Understudied Fish In The Marine Aquarium Trade, Alice Wynn, Jemelyn Baldisimo, Gabrielle Baillargeon, Michael Tlusty, Andrew Rhyne

Biological Sciences Faculty Publications

The marine aquarium trade (MAT) harvests millions of coral reef fishes from the wild yearly. While the MAT supports fishers, hobbyists and marine education, harvested fishes are crucial in maintaining coral reef health and balanced marine cycles within their native habitats. Understanding the impact of the MAT on fish populations is critical for sustaining the trade in the long-term. Productivity-susceptibility analyses (PSAs) offer semiquantitative methods of analyzing the productive capacity of each fish stock, as well as its susceptibility to overfishing. The present study revises and expands upon a PSA conducted by Baillargeon et al. (2020) that focused on 32 …

Dengue Virus Modulates Critical Cell Cycle Regulatory Proteins In Human Megakaryocyte Cells, Swarnendu Basak, Shovan Dutta, Supreet Khanal, Girish Neelakanta, Hameeda Sultana

Biological Sciences Faculty Publications

Suppression of human megakaryocytes by dengue virus (DENV) infection significantly reduces the platelet count that eventually leads to thrombocytopenia, severe dengue and death. To understand DENV interactions with megakaryocytes, we investigated the cell cycle in leukemic human megakaryocytic in vitro cell line (MEG-01 cells). Megakaryocytes are known for complex endomitotic cell cycle leading to their polyploidy state. Our study shows that DENV uses these polyploid cells for its replication. Understanding the modulation of DENV-mediated cell cycle regulation in megakaryocytes is therefore highly important. We show that DENV2 (serotype 2) infection significantly modulates cell cycle signaling. Our protein profile microarray data …

Analyzing Microbial Communities In Porites Astreoides, Sanaa Caldwell, Katie Parker, Daniel Barshis

Biological Sciences Faculty Publications

Coral reefs are vital marine ecosystems that support many different species and ecosystem services through protecting coastlines from storms and erosion, providing raw materials for medication, and facilitating diversity amongst marine species. Anthropogenic climate change is causing ocean temperatures to exceed the range of coral thermal tolerance resulting in more coral bleaching events globally. However, some corals have the capacity to withstand high temperatures through different thermal tolerance strategies. A balanced microbial community plays a critical role in coral health and recent studies have indicated that a balanced microbiome is associated with temperature-stress tolerant corals. Yet, there is a severe …