Cybersecurity Commons^™

Adversarial Robustness Of Perceptual Hashing Systems: A Unified Security Evaluation Framework, Avijit Roy

Student Theses

Social network platforms, child safety organizations, and image provenance systems use perceptual hashing to identify known child sexual abuse material (CSAM), support content moderation and reverse image search, and verify image integrity. Perceptual hashing works by producing similar fingerprints for visually similar images, even after common transformations such as compression, resizing, or minor brightness changes. This useful similarity-preserving property also creates an adversarial attack surface, as attackers can use AI-assisted or conventional image manipulation techniques to move a hash across a matching threshold while maintaining visual similarity, often without access to specialized hardware.

The security failures produced by adversarial attacks …

The Security Of Llm-Generated Code, Christopher Brian Gonzalez Ayala

Student Theses

The rapid adoption of Large Language Models (LLMs) in software development has transformed coding practices by enabling automated code generation, completion, and optimization. Despite these advantages, concerns persist regarding the security and reliability of LLM-generated code. This study presents a comprehensive evaluation of both the functional correctness and security of code produced by three prominent LLMs as of early 2026. A total of 4,800 code snippets were generated using 100 security-focused programming prompts derived from the OWASP Top 10:2025, translated across eight natural languages and two phrasing styles (literal and natural developer-oriented prompts). To assess performance, a multi-stage experimental framework …

Sound Detection Of Memory Leaks In Llvm Ir Programs Using Accumulation Analysis, Robert Blacha

Theses

Resource leaks occur when a limited resource such as memory is allocated by a program and needlessly held past the point of use. Leaks can lead to a degradation of services which can be specifically triggered with malicious behavior, for example abusing a memory leak in a program to cause a server to slow down and crash for a denial-of-service attack.

Prior work has demonstrated that accumulation analysis provides a sound detection of resource leaks with a working implementation for programs written in Java. While useful, current implementations are limited to programs written in Java, which has a garbage collector, …

Anonymity And Accountability In Secure Messaging, Erin Kenney

Dissertations

Encypted messaging has become more and more prevalent as time moves on, and its benefits in assuring privacy cannot be overstated, but it also brings along with it concerns on how to moderate platforms where all messages are hidden. Message Franking, followed by Traceback systems, addressed these concerns by allowing the sender of a message to be proven when reported, even for forwarded messages in the case of Traceback, however these systems damage the privacy guarantees that originally motivated encrypted messaging to begin with.

In practice, even without those concerns encrypted messaging alone is not enough to prevent the most …

Distributed File Carving, Brad J. Baudin

LSU Master's Theses

File carving is a fundamental technique in the digital forensics community, enabling analysts to recover deleted files from disk images without relying on filesystem metadata; however, as storage capacities continue to increase, modern file carving tools face significant scalability challenges, with carving time growing substantially alongside disk image size, particularly in the presence of file fragmentation. Fragmentation, a common behavior in modern filesystems, distributes file data across non-contiguous disk blocks to maximize space utilization, and in large disk images this distribution can span wide logical distances, increasing the search space and reducing carving efficiency, causing traditional approaches to struggle within …

Meeting The Moment With Ai-Employer Informed Education, Brent Terwilliger, John Faraca

Publications

As artificial intelligence transforms aviation, aerospace, and autonomy-related sectors, higher education must adapt to meet evolving workforce demands. This session shares emerging findings from a nationwide study led by Embry-Riddle Aeronautical University, focused on employer perceptions of AI adoption, responsible use, and workforce preparedness in domains including uncrewed systems, space systems, robotics, and advanced air mobility. Based on a structured survey and follow-up interviews, the presentation explores how organizations are using AI tools, from generative platforms to enterprise systems, and defining effective and inappropriate use in operational contexts. Participants will gain insight into critical concerns (e.g., data privacy, compliance, security, …

Security Assessment Of A Machine Learning Approach To Generate And Validate Digital Signatures, Juan Ortiz Couder

Doctoral Dissertations and Master's Theses

Cybersecurity has become a global concern as cyber-attacks have become more common, and the cost of the damage caused by them continues to increase. There are several approaches to improve the cyber security of systems such as Digital Signatures, hashing, watermarking, and encryption among others. Digital Signatures are a cryptographic technique used to verify the authenticity and integrity of digital messages or documents. Digital Signatures use a combination of hashing and public-private key encryption to verify the authenticity and integrity of videos, just as they are used for documents and messages. As a result of using a combination of other …

Enhancing Control Charting Schemes And Exploring New Assessment Metrics To Advance Quality Control And Cyber-Attack Detection In Manufacturing, Ahmad Al Majali

Dissertations

The increasing integration of digital technologies and industrial control systems in modern manufacturing has introduced new cybersecurity vulnerabilities within cyber–physical production environments. Malicious actors can exploit these vulnerabilities to induce subtle process deviations that degrade product quality while remaining undetected by conventional statistical monitoring tools. Such attacks can be deliberately engineered to manipulate process behavior through transient shifts that vary in magnitude, duration, and frequency. Despite extensive research on transient shifts caused by assignable causes in Statistical Process Control (SPC), limited attention has been given to intelligently designed cyber–physical attacks that exploit the structural characteristics and limitations of control charting …

Friend Or Foe? The Benefits And Risks Of Llms In Cybersecurity, Niklas P. Dobler

Honors Theses

The rapid growth of Large Language Models (LLMs) and their continuous increase in capabilities have affected many professions and people. Due to advancements in areas such as coding and data analysis, they are now also being utilized in Cybersecurity. Recent research has examined their use in many different areas such vulnerability detection in code and analyzing network traffic. With this rapid growth, most organizations around the world are eager to advance faster than their competition, with limited considerations for the potential harm and risks these tools could bring. Some research has been conducted on malicious uses, but as the benefits …

Post-Quantum Cryptography Encryption Implementation For Messaging App, Callum S. Ward

Theses/Capstones/Creative Projects

This paper and complementary capstone project aim to explore the state of post-quantum cryptography today by defining the algorithms with which quantum computers can decipher modern asymmetric cryptographic algorithms in exponentially accelerated time, exploring national standards body NIST’s recommendations to circumvent these weaknesses with post-quantum solutions, and implementing recommended algorithms in my group’s project for the UNO Computer Science Capstone course, LockTalk. After having decided on ML-KEM for quantum-resistant asymmetric key transfer and AES-256 for symmetric message encryption and decryption, I was able to cryptographically encode messages to obscure their plaintext values from communication interceptions without any discernible increase in …

Blockchain Message Integrity For Messaging App: Python-Based Implementation Of Blockchain-Backed Verification And Tamper Detection, Brendan J. Farrell

Theses/Capstones/Creative Projects

With the rapid development and use of digital communication, the need for maintaining the integrity and authenticity of transmitted information becomes more pressing than ever.  However, existing methods of data exchange have several flaws and drawbacks such as reliance on centralized networks which are subject to manipulation, modifications, and potential failures.  Thus, the current project offers an innovative approach to improving the integrity and detection capabilities of messages in real-time communication platforms using the power of blockchain technology.  The proposed solution uses the inherent features of blockchain-based systems to ensure secure and safe message transmission.

Message Malware: File Vulnerability Scanning In Messaging Apps, Miah Mason

Theses/Capstones/Creative Projects

As messaging platforms become primary communication hubs within highly secure environments, they introduce significant vulnerabilities regarding file sharing with potential malicious content. This research, an honors extension of the Northrop Grumman sponsored Capstone project ‘LockTalk’, evaluates the technical abilities of automated file scanning methods within messaging platforms like Slack, Microsoft Teams, or our own developed platform LockTalk. This paper investigates a variety of scanning methods and their applications, with particular emphasis on comparing the qualities of static scanning, used in signature-based detection, and dynamic scanning with heuristics. Furthermore, this paper investigates the differences and advantages of both End-to-End Encryption (E2EE), …

Using Ai For Data Loss Prevention, Camden A. Wright

Theses/Capstones/Creative Projects

Data Loss Prevention (DLP) systems play a critical role in protecting modern systems that handle sensitive information from both accidental and malicious exposure. Traditional DLP approaches often rely on static rules and methods that can struggle to adapt to complex and evolving data patterns. This paper presents a hybrid DPL system that integrates machine learning-based message classification, rule based policy enforcement, and context-aware access control to improve both detection accuracy and decision reliability. In addition, the system introduces a second stage access control model that evaluates user context, including role of clearance level and job title to determine whether access …

The Privacy Paradox: How Does Concern About Privacy Impact Actions In The Digital Age?, Julia Laduke

Honors Theses

The privacy paradox occurs when people claim to care about their digital privacy, but do not take actions to keep their data from being spread across the internet. This study examines college students, being primarily Generation Z, and their concerns and actions regarding digital privacy and security. A survey of 15 college students, 7 in humanities and 8 in STEM, was used to analyze their thoughts and concerns about their digital privacy. This survey also asked whether they took actions concerning their privacy, and if so, what tools they used to protect it. The results show that about 50% of …

F.L.A.I.R. -- A Flow-Level Autoencoder For Intrusion Recognition, Joseph P. Dumond

Electrical Engineering and Computer Science Undergraduate Honors Theses

Industrial Internet of Things (IIoT) networks underpin critical infrastructure worldwide, yet securing them remains an open challenge. Traditional intrusion detection systems require labeled attack data for training, a resource that is rarely available in real industrial deployments. They also fail against novel threats, a model trained on known attacks has no basis for detecting anything outside its training set. This thesis presents a Flow-Level Autoencoder for Intrusion Recognition, or FLAIR, a fully unsupervised deep learning system for network intrusion detection in IIoT environments. FLAIR is built on a Gated Recurrent Unit (GRU) autoencoder trained exclusively on normal network traffic. Rather …

A Case Study On Using Large Language Models To Drive Convergence-Oriented Literature Discovery In Critical Infrastructure Security, Caden J. Williamson

Electrical Engineering and Computer Science Undergraduate Honors Theses

In the world of cybersecurity, the rapid development of artificial intelligence proposes a constant challenge for researchers to defend critical infrastructure. Attacks on critical infrastructure can be catastrophic, and emerging strategies of cyber-adversaries that implement leading AI models can expose vulnerabilities in critical infrastructure much faster than previous tools. To defend against this emerging threat, the Cybersecurity Research Working Group at the University of Arkansas is aiming to develop a cross-domain and cross-discipline center of excellence. To support this effort, the group is writing a literature review on the topics of AI and critical systems security. Literature review is an …

Polyglot File Detection For Forensic Investigations, Chase Stevens

Graduate Theses and Dissertations (2019 - present)

As technology has become far more ubiquitous over the years, so too has the amount of digital evidence that can and needs to be collected and processed. Forensic tools are developed in response to the growing need, but are limited to what they are programmed to do. One such forensic tool is Autopsy, one of the most widely used open-source tools. Autopsy uses known file-type signatures (e.g., headers, trailers) to identify and recover files from forensic images. Polyglot files introduce a unique problem to both these forensic tools and investigators alike. In the context of the research conducted, polyglot files …

Detecting Sophisticated Cyberattacks On Public Water Infrastructure, Ayrton Purdy

Graduate Theses and Dissertations (2019 - present)

In recent years there has been an increasing number of cyberattacks on public water generation and distribution systems. Advanced persistent attackers could usurp sensors and control systems to contaminate public drinking water. In order to conceal their malicious activity, they can manipulate sensor data flows to give the appearance of normal activity. The compromised sensors would report normal chemical levels even though unsafe water is entering the distribution system. In response, this research proposes a multi-sensor, cross-comparison approach to anomaly detection. The proposed approach is designed to detect sophisticated cyberattacks which are not easily detectable using traditional cyber tools. The …

Developing A Framework For Microchip Design Recovery, Eric Diep

Graduate Theses and Dissertations (2019 - present)

Due to the increase in diverse chip production over the past decade, reverse engineering has become a difficult and daunting task. This research develops a methodology for microchip design recovery, seeking to validate and reproduce prior approaches to physical reverse engineering using low-cost tools and techniques. We used mechanical hardware abrasion tools and techniques to delayer and capture silicon integrated chip (IC) layout. We focused on the Mifare Classic EVl microchip, commonly implemented in public transit/transportation cards, to extract information for design recovery. The research explores limitations and advantages of mechanical abrasion and optical microscopy in context to modem chip …

Improving Fairness On Semantic Segmentation Using Large Language Models, Samuel E. Burggraf

Electrical & Computer Engineering Projects for D. Eng. Degree

As machine learning systems are increasingly integrated into critical decision-making processes, ensuring fairness in their design and implementation has become a significant concern. While fairness research has primarily focused on specific protected attributes, less attention has been given to spatial fairness, which can affect individuals at specific locations. If fairness is not addressed, models may systematically underperform in certain regions or across populations which can lead to unequal access to accurate predictions and potentially biased decision-making. Fairness considerations should extend across all machine learning applications to align with the National Institute of Standards and Technology (NIST) guidelines of fair and …