Summer Immersion Experience Programs
A User-Centric Predictive Model of Perceived Risk in Generative AI
This project explores how users perceive privacy risks when interacting with Generative AI (GenAI), such as ChatGPT. By analyzing user-generated prompts and their willingness to share personal data, the research aims to develop a predictive model that assesses privacy risks in real-time. The study focuses on:
- User Prompt Analysis – Identifying sensitive information shared in AI-generated interactions.
- Inversion Attack Simulation – Testing how attackers might extract unintended private details.
- Risk Prediction Modeling – Creating a statistical model to assess and mitigate privacy threats.
This interdisciplinary research, combining computer science, engineering, and statistics, will help improve AI transparency and empower users with greater awareness of their digital privacy.
Advanced Data Engineering Lab
The concentrated work of the Advanced Data Engineering Lab is on statistical learning for systems modeling, control, and optimization. The research is strongly data-driven, engineering practices and management science combined with mathematical models and data-driven methods to lead significant changes in complex systems.
AI: Integrating Domain Knowledge to Improve Performance of LLM Agents
This project aims to develop an advanced framework that integrates additional domain knowledge (e.g., practice guideline databases, and terminology knowledge bases) to improve the performance of LLM agents in medical Question-Answering (QA) tasks. This project focuses on improving performance metrics, mitigating hallucinations, and enhancing user experience through tailored feedback. The framework will develop QA agents using open source pre-trained LLM models as baselines. By integrating domain knowledge at inference time, the framework will improve performance in understanding input questions, providing verified answers, and reducing incorrect outputs in QA tasks. The result of this project will be a robust system that can be applied to various domains with high risks in using LLM agents.
Computer Vision: FaceDeep Detection
The FaceDeep Detection Project aims to develop an advanced facial recognition system that leverages deep learning algorithms to accurately identify and verify individuals in various settings. This project focuses on enhancing security measures, streamlining authentication processes, and improving user experience across digital platforms. By training the model on a diverse dataset of facial images, the system will be capable of detecting subtle facial features and expressions with high precision, even in challenging conditions such as varying lighting, angles, and occlusions. The outcome of this project will be a robust, scalable solution that can be integrated into security systems, personal devices, and access control mechanisms, providing a seamless and secure method of identity verification.
Computer Vision: Pedestrian Behavior
The Computer Vision on Pedestrian Behavior Project aims to analyze and understand the patterns and dynamics of pedestrian movements in various environments using advanced computer vision techniques. By deploying state-of-the-art image and video analysis, this project seeks to identify common behaviors, predict movements, and assess the interactions between pedestrians and their surroundings. The insights gained could be pivotal for enhancing urban planning, improving public safety, and developing autonomous vehicle systems that are better equipped to navigate complex human environments. Moreover, the project's findings have the potential to contribute to the design of smarter, more responsive pedestrian networks in smart cities.
Controlling Access to Knowledge in LLMs
As large organizations fine-tune company-specific models for their employees, security is becoming more critical. Specifically, not all knowledge should be accessible to all employees. Moreover, it is infeasible to train large models for every sub-group within the organization because limiting the training data could reduce the model’s performance, and tracking thousands of models would be infeasible to scale. Hence, for this project, students will work to implement an access control system within LLMs such that user information (e.g., username, department, etc.) and the organizations current access control rules can be considered before providing a user with a generation. The goal is to develop an end-to-end system that handles access control that is also robust to adversarial attacks.
Fine Motor Interaction using Full Body Pose Estimation for Children with Autism
The "Fine Motor Interaction using Full Body Pose Estimation for Children with Autism" project aims to assess the practicality and efficacy of utilizing Full Body Pose Estimation technology to enhance fine motor skills development in children with autism through a feasibility study. Employing sophisticated pose estimation algorithms, the project seeks to accurately capture and analyze the intricate movements of these children, providing real-time insights into their motor abilities. Through the incorporation of customizable interaction parameters and the adaptation of virtual environments based on general needs, the project aims to contribute valuable insights into improving therapeutic interventions for children with autism. The study could potentially offer a novel and effective approach to fine motor skill development, impacting the broader landscape of interventions for this population.
Identification of Heat Islands
The Identification of Heat Islands in the City of San Antonio Downtown project seeks to utilize machine learning algorithms and digital twin technology to identify and analyze heat island phenomena within the downtown area. By leveraging datasets encompassing environmental factors, urban infrastructure, and geographical features, this project aims to develop predictive models capable of pinpointing areas prone to heat islands. Through the integration of machine learning techniques and digital twin simulations, the project endeavors to provide insights into the underlying causes of heat islands and propose potential mitigation strategies. The outcomes of this research could inform urban planners, policymakers, and stakeholders in implementing measures to alleviate the impacts of heat islands and enhance the overall livability and sustainability of urban environments.
Illuminating Tomorrow: An Immersive Experience in Trustworthy Silicon Photonics AI Chip Design
Silicon Photonics (SiPh) is redefining AI hardware with ultra-fast, energy-efficient processing, but securing these systems remains a critical challenge. This immersive summer program at The University of Texas at San Antonio offers hands-on training in the design, fabrication, and security of Trustworthy SiPh AI chips, bridging hardware design, AI acceleration, and cybersecurity. Participants will gain expertise in cutting-edge security techniques tailored for photonic AI accelerators, preparing them for graduate research and high-impact industry careers. This program builds on the growing academic and industrial interest in Photonic AI Security, highlighted by Dr. Dang’s (the program coordinator) invited talks and tutorials at premier conferences such as IEEE/ACM ICCAD 2024 and DATE 2025.
The Impact of Software Changes on Accessibility
As software systems evolve, frequent updates and modifications can unintentionally impact accessibility features, affecting how users with disabilities interact with digital platforms. This project aims to analyze software changes and their consequences for individuals with disabilities, focusing on how updates in user interfaces, functionality, and compliance with accessibility standards influence usability.
Machine Learning: Fair House Value Prediction
The Housing Price Prediction Project aims to develop a machine learning model that can accurately forecast the market value of residential properties based on a range of features such as location, size, number of bedrooms, amenities, and historical sales data. Utilizing various regression techniques and data preprocessing methods, this project will analyze and learn from a comprehensive dataset of housing transactions. The goal is to provide potential buyers and sellers with insightful predictions to make informed decisions in the real estate market. By leveraging advanced algorithms and predictive analytics, the project seeks to enhance transparency, efficiency, and fairness in property valuation, ultimately benefiting both real estate professionals and consumers.
Machine Learning Optimization & Signal Processing (MELOS)
MELOS is under the guidance of Dr. Panagiotis (Panos P.) Markopoulos. The focus of the research is dedicated to addressing complex and significant issues in the fields of machine learning, data analysis and signal processing. The overarching goal is to advance the growth of efficient, explainable and reliable artificial intelligence. Read more about MELOS Lab.
Natural Language Processing (NLP) - Automated Customer Support System
Objective: Develop a system that leverages Large Language Models to provide real-time, intelligent customer support across various digital platforms (e.g., web chat, social media, and email). This project aims to create an automated customer support system that utilizes the capabilities of LLMs in NLP to understand customer queries in natural language, process them, and deliver accurate, context-aware responses. By integrating LLMs, the system will be able to handle a broad spectrum of inquiries, ranging from simple FAQ-type questions to more complex troubleshooting and personalized advice. The system will also learn from each interaction, improving its accuracy and efficiency over time. The goal is to enhance customer satisfaction by reducing response times and improving the quality of support, while simultaneously decreasing the workload on human customer service representatives.
Open Cloud Institute
The Open Cloud Institute was created in 2015 as part of an initiative to develop degree programs in cloud computing and big data. The focus is now on bringing the latest developments of cloud and edge computing to the university through sponsored seminars, workshops, internships and fellowships, and collaboration activities with other key institutes and centers across UTSA
Privacy by Design in Cloud IoT
With computer databases emerging in the 1960s, privacy was defined as individuals’ control over how, when, and to what extent information about them is shared. Today, as technologies such as cloud computing and the Internet of Things reshape digital landscapes, privacy concerns have evolved further. Modern privacy considerations extend beyond data collection by businesses, encompassing complex relationships, interactions, and possible conflicts among multiple parties in shared or multi-user environments. This project will explore the creation of a comprehensive Privacy by Design framework that enables transparency, control, and collaborative privacy management services in cloud environments.
Privacy Risk in Large Language Models
Despite the popularity of large language models (such as ChatGPT) and increasing user base, these models pose new privacy threats to personal information due to their data-intensive nature. The goal of this project is to explore the impact of users’ awareness and willingness to share their information on the adoption of GenAI models while assessing the accompanying privacy risks.
Quantifying Arguments at Scale using Large Language Models
Misinformation can spread because of contradictory evidence in research articles, particularly when predatory venues are considered. In 2020, COVID-19-related research constituted 4% of the world's research papers, making it difficult for researchers and public health officials to remain informed. Moreover, in these articles, there is a substantial amount of contradictory COVID-19-related research published. One article may state an item as incorrect even though hundreds of other articles state it as correct. Hence, to fully understand the research, it is important to understand the scientific consensus of specific arguments (e.g., how many papers make each pro and con argument for a specific claim). For this project, given a specific research topic, we will explore retrieval-augmented large language models to 1) extract claims from research articles, 2) match the claims that state the same argument, and 3) match claims that state the opposite/contradictory argument.
ScooterLab
ScooterLab is a National Science Foundation (NSF) funded community research infrastructure initiative at the University of Texas San Antonio's School of Data Science. This publicly-available micro-mobility testbed and crowd-sensing/crowd-sourcing infrastructure will provide researchers access to a community of riders and a fully operational fleet of customizable dockless e-scooters. The research team is actively working on developing infrastructure prototypes that can be easily equipped with cutting-edge sensors enabling the real-time collection of detailed research data during rides.
Smart City: Optimized Shaded Routes for Urban Walkers
The Smart City Path Planning with Maximum Shade project leverages digital twin technology to optimize pedestrian routes for maximum shade coverage. This innovative approach utilizes 3D city modeling and solar trajectory analysis to identify and recommend the coolest paths for city dwellers. Aimed at enhancing urban liveability and promoting eco-friendly transport, the project is instrumental for urban developers in strategically planning green spaces and pedestrian-friendly infrastructure. It's a step towards sustainable urban living, providing a dual benefit of comfort for pedestrians and data-driven insights for city enhancement.
Software Change Management in an Open-Source Environment
In open-source projects, software change management relies on community-driven decision-making, where feature requests, bug reports, and code contributions shape software evolution. Unlike proprietary development, open-source changes are managed transparently on platforms like GitHub, where maintainers balance user needs, software quality, security, and privacy concerns. Challenges include ensuring backward compatibility, addressing conflicting stakeholder interests, and maintaining compliance. This project aims to analyze these challenges and provide solutions to improve software change management in an open-source environment.
SPriTELab
The SPriTELab's mission is for groundbreaking and impactful security and privacy research with the goal of improving humanity's trust and reliance in modern computing systems, applications, and technology. SPriTELab is an acronym for Security, Privacy, Trust, and Ethics in Computing.
