Cybersecurity Commons^™

Biosecure-Llm Framework: Protecting Llms From Cyberbiosecurity Threats And The Case For Independent Ai Safety Governance, Xavier-Lewis Palmer, Lucas Potter, Srdjan Lesaja, Sotirios Karathanasis, Mohammad Ghasemigol

Computer Science Faculty Publications

Large Language Models (LLMs) are becoming critical infrastructure in scientific, healthcare, and governmental contexts. As frontier AI laboratories increasingly partner with government agencies, a fundamental question arises: Who should control the safety and policy-enforcement layers that constrain model behavior? Current safety mechanisms (LLM guardrails) are typically designed for generic "harmlessness" and operate by detecting semantic patterns and refusing requests. However, they are inadequate governance instruments because they cannot implement auditable, domain-specific controls tied to external regulatory policy objects (e.g., control lists or rules governing personally identifying information). Even a perfectly aligned model is not able to express institution-specific policy without …

An Explainable Cs-Mitigation Triangular (Ecsmt) Framework To Secure Graph Neural Networks, Sabah Ettahri, Sergio Pallas Enguita, Chung-Hao Chen, Wen-Chao Yang

Electrical & Computer Engineering Faculty Publications

This research addresses cyber risk by defending against backdoor attacks on Graph Neural Networks (GNNs). We propose the Explainable Complex System-Mitigation Triangular (ECSMT) Framework, which integrates Robust Training, Graph Regularization, and Data Sanitization into a lightweight, hardware-efficient defense layer. To evaluate structural generalizability, we conducted empirical evaluations across three distinct benchmark domains (AIDS, MUTAG, and PROTEINS) using a Graph Isomorphism Network (GIN) backbone. Under a baseline 5% backdoor subgraph trigger injection ratio, ECSMT achieves excellent utility retention, securing a Clean Accuracy (CA) of 97.33% (±0.62%) while reducing the Attack Success Rate (ASR) from 97.00% down to 69.45% on the primary …

A Knowledge-Driven, Ai-Assisted Cyber Defence Framework For Iomt Remote Patient Monitoring, Kulsoom S. Bughio, David M. Cook, Abdul M. Unar

Research outputs 2022 to 2026

The rapid adoption of Internet Medical Things (IoMT) technologies in remote patient monitoring has reshaped healthcare delivery by enabling continuous, real-time clinical observation outside traditional care settings. However, this shift has also expanded the cyber-attack surface across heterogeneous, resource-constrained medical devices, wireless networks, cloud services, and third-party platforms. In cyber warfare, healthcare has become an incorporated target of geopolitics, with hospitals, remote monitoring systems, and emergency health systems being used to broaden the attack surface for adversaries to exploit. Existing security approaches for IoMT environments remain largely manual, fragmented, and reactive, limiting their effectiveness in dynamically assessing vulnerabilities and supporting …

Ordered Mini-Batch Training For Differentially Private And Encrypted Logistic Regression, Ryan Leone

Theses, Dissertations and Culminating Projects

Logistic regression has found extensive use as a supervised machine learning algorithm due to its simplicity and efficiency in binary and multivariate classification tasks. As data sharing grows across connected devices, safeguarding sensitive personal and industrial information is of increased importance. Privacy-preserving machine learning techniques such as differential privacy and homomorphic encryption offer mathematically rigorous security guarantees, but introduce difficult accuracy, privacy loss, and computational overhead issues. This thesis investigates PPML for logistic regression through a collaborative mini-batch training framework. I propose and implement an ordered mini-batch strategy, compare it to standard shuffled methods, then integrate differential privacy noise injection …

Energy-Efficient Security For Narrowband Iot Using Blockchain And Ep-Cumac, Hafizullah Kakar

UNF Graduate Theses and Dissertations

The Narrowband Internet of Things (NB-IoT) continues to expand but faces challenges such as cryptographic overhead and energy consumption. Security frameworks such as blockchain and Energy-Performance Cumulative Message Authentication Codes (EP-CuMAC) rely heavily on SHA-256, which is not optimized for energy-limited devices.

This work unifies two complementary approaches, a hybrid blockchain-based NB-IoT framework and an EP-CuMAC-based framework, by engineering their cryptographic core with an Energy Complexity Model-optimized SHA-256 (ECM-SHA256). ECM applies parallel memory-bank mapping and block-level access optimization to reduce redundant power usage while preserving algorithmic integrity.

Experimental evaluation on identical Intel DDR3 systems using pyRAPL shows energy savings of …

Ai-Driven Penetration Testing For Arm Systems: A Comprehensive Framework With Experimental Validation, Matthew Ragsdale

College of Graduate Studies: Theses & Dissertations

The convergence of artificial intelligence and cybersecurity presents new opportunities for automated penetration testing capable of discovering, prioritizing, and remediating vulnerabilities at machine speed. However, deployment on resource-constrained ARM platforms remains unexplored despite ARM’s dominance in mobile, IoT, and edge computing with over 280 billion chips deployed globally. This thesis presents systematic experimental evaluation of AI-driven penetration testing across four paradigms—traditional machine learning, deep learning, large language models, and reinforcement learning—on three ARM platform tiers: Raspberry Pi 5 (8GB, Cortex-A76), Radxa ROCK 5B Plus (16GB LPDDR5 with NPU), and NVIDIA Jetson Nano (4GB with Maxwell GPU). The experimental framework generates …

Quantum Readiness In Cybersecurity Education: A Framework For Preparing The Next Generation In The Post-Quantum Era, George Antoniou

Faculty and Staff Publications & Presentations

This framework addresses the critical gap between post-quantum standards and workforce readiness. Shor's algorithm demonstrates that sufficiently powerful quantum computers can break the cryptographic foundations of internet security. While the cryptography research community has developed quantum-resistant algorithms, educational institutions have not prepared students to implement these solutions. Recent surveys show fewer than half of organizations have begun planning for post-quantum cryptography (PQC) transitions (Entrust Cybersecurity Institute, 2024; U.S. Government Accountability Office, 2023; (ISC)², 2024). The NICE Framework (Newhouse, Keith, Scribner, & Witte, 2017) outlines the knowledge and skills that cybersecurity professionals should possess. The framework omits post-quantum cryptography entirely. Organizations …

Patterns Of Llm Weaponization: A Comparative Analysis Of Exploitation Incidents Across Commercial Ai Systems, George Antoniou

Faculty and Staff Publications & Presentations

This comparative study examines patterns of Large Language Model (LLM) weaponization through systematic analysis of four major exploitation incidents spanning 2023-2025. While existing research focuses on isolated incidents or theoretical vulnerabilities, this study provides the first comprehensive comparative framework analyzing exploitation patterns across state-sponsored cyber-espionage (Anthropic Claude incident), academic security research (GPT-4 autonomous privilege escalation), social engineering platforms (SpearBot phishing framework), and underground criminal commoditization (WormGPT/FraudGPT ecosystem). Through comparative analysis across eight dimensions—adversary sophistication, target selection, exploitation techniques, autonomy levels, detection evasion, attribution challenges, defensive gaps, and capability democratization—this research identifies critical cross-case patterns informing defensive prioritization. Findings reveal three …

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 …

Nonlinear Phase Space Analysis For Anomaly Detection In Ros 2 Communications: Detecting Man-In-The-Middle Attacks In Simulated Environments, William L. Locklier

Graduate Theses and Dissertations (2019 - present)

Robot Operating System 2 (ROS 2) marks a significant advancement over its predecessor through the transition from a centralized to a decentralized architecture, integrating the Data Distribution Service (DDS) to support real-time, scalable communications. Despite these improvements, inherent vulnerabilities in the ROS 2 communication stack continue to leave these systems exposed to sophisticated network-based attacks. This study leveraged nonlinear phase space analysis (NLPSA) as an intrusion detection system (IDS) to detect man-in-the-middle (MitM) attack anomalies in ROS 2 traffic. Grounded in Takens’ embedding theorem, NLPSA reconstructs the phase space of communication features and compares the resulting structure against a baseline …

Quantum Readiness In Cybersecurity Education: A Framework For Preparing The Next Generation In The Post-Quantum Era, George Antoniou

Faculty and Staff Publications & Presentations

The rapid advancement of quantum computing represents both a revolutionary opportunity and an existential threat to contemporary cybersecurity infrastructure. While quantum computers promise unprecedented computational capabilities, they simultaneously pose a critical risk to current cryptographic protocols that protect sensitive data, financial systems, and national security frameworks. Post-quantum cryptography (PQC) standards, recently formalized by NIST in 2024, provide a roadmap for quantum-resistant encryption. However, a significant gap exists between technological advancement and educational preparedness, with most cybersecurity curricula failing to adequately prepare students for the quantum era. This paper addresses the urgent need for comprehensive quantum readiness in cybersecurity education across …

Teaching Cybersecurity And Ai Across Borders: From Foundations To Ethics, George Antoniou

Faculty and Staff Publications & Presentations

This presentation examines how interdisciplinary course design in AI and cybersecurity can expand undergraduate research while directly supporting career readiness. At Lynn University, the Foundations of Cybersecurity & AI course was updated to serve as the entry point for both Cybersecurity and Data Analytics majors. The course integrates case studies, digital forensics and cloud security labs, and applied exercises with AI-enabled defense-in-depth strategies. Students build core technical competencies while engaging in course-based research that mirrors industry practice. As part of a Fulbright grant, a complementary course, AI & Ethics, was developed for the University of Tirana. Proposed as a mandatory …

Optimizing Cybersecurity Through Ai Predictive Analytics And Human Expertise, Cathy Mae C. Dutong

Journal of the Symposium of University Research and Creative Expression

Project Mentor(s): Hideki Takei, DBA

As cybersecurity threats evolve in complexity and scale, the reliance on artificial intelligence (AI) has become increasingly prevalent across both public and private sectors. This study examines the dual role of AI-driven predictive analytics in strengthening organizational cybersecurity, while addressing the ongoing need for human oversight. Through a mixed-method approach, combining survey data from cybersecurity professionals with an extensive literature review, this research analyzes AI's capacity to detect emerging threats, the systemic challenges associated with AI integration, and the indispensable role of human expertise in interpreting AI outputs. Findings indicate that while AI enhances proactive …

Machine Learning And Crime Prevention, Emily Lizewski

Student Theses

Predictive policing uses machine learning to analyze crime patterns and help law enforcement better efficient use their resources. These tools can improve accuracy by highlighting complex trends in large sets of data. While this technology has its advantages, it also raises important ethical and social questions. Within this paper we looks at how predictive policing works, focusing on the machine learning models often used such as decision trees, random forests, gradient boosting, and models that factor in both time and location. It also explores how these tools might unintentionally reinforce biases already present in historical crime data. In reviewing the …

Robustness Investigation, Detection, And Defense Of Deep Learning Models Against False Data Injection, Amirhossein Nazeri

All Dissertations

This dissertation addresses the critical challenge of adversarial robustness in deep learning systems, focusing on two fundamental domains: time-series prediction and object detection. As these AI systems become increasingly deployed in safety-critical applications from power grid management to autonomous vehicles their vulnerability to adversarial attacks poses significant risks to infrastructure and human safety.

The first contribution introduces a novel stealthy black-box False Data Injection (FDI) attack specifically designed for quasi-periodic time-series data. Unlike existing attacks that produce easily detectable anomalies, our method generates adversarial perturbations that preserve the underlying periodicity and statistical properties of the data, effectively bypassing traditional anomaly …

Towards Securing Ai Systems: Investigating Threats In Multimodal Autonomous Driving & Rag Systems, Saket Sanjeev Chaturvedi

All Dissertations

Artificial Intelligence (AI) systems have become central to high-stakes applications such as autonomous driving and language-based decision support. As their deployment accelerates, ensuring the security and trustworthiness of these systems becomes paramount. Among the most stealthy and potent threats are backdoor attacks, where models behave as expected under normal conditions but exhibit malicious behavior when triggered by specific inputs, either digital or physical.

This thesis investigates novel backdoor and adversarial vulnerabilities across two emerging classes of AI architectures: (1) multimodal 3D object detection systems that fuse LiDAR and camera data, and (2) Retrieval-Augmented Generation (RAG) systems that pair large language …

Securing Ai-Generated Code, Andreas E. Nelson

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

The increasing use of AI for code generation presents significant security challenges, as these tools often lack inherent security awareness and can produce vulnerable code. This paper investigates these security risks, outlining common types of vulnerabilities (such as injection flaws and improper resource handling) found in AI-generated code. It further explores and evaluates mitigation techniques aimed at im-proving code security, including model fine-tuning and adversarial strategies like Security Verifier Enhanced Neural Steering (SVEN). Findings indicate that while current methods offer promising ways to reduce vulnerabilities, ongoing research and development are crucial for the secure and responsible deployment of AI in …

Enhancing Proof-Of-Learning Security Against Spoofing Attacks Using Model Watermarking, Ozgur Ural

Doctoral Dissertations and Master's Theses

With the rapid expansion of machine learning (ML) technologies across diverse domains such as healthcare, finance, and autonomous systems, ensuring secure and trustworthy training methodologies has become more critical than ever. Proof-of-Learning (PoL) has recently emerged as a foundational mechanism for verifying the computational effort invested in training ML models, thereby certifying the authenticity and reproducibility of the training process. Yet PoL, when deployed in isolation, remains vulnerable to sophisticated spoofing attacks that manipulate its subset-verification pathways and tolerance parameters. In parallel, model watermarking has become indispensable for safeguarding intellectual property and detecting unauthorized model usage. Motivated by these complementary …

Context-Switch Attacks: Understanding And Mitigating The Threat To Llm Applications, Sydney Holder, Bivin Sadler

SMU Data Science Review

Large Language Models (LLMs) are transforming conversational AI, yet their dependence on prompt-supplied context exposes them to context-switch attacks that covertly steer dialogue toward sensitive or malicious ends. A 70 one-sided conversation transcript evaluation set was constructed spanning various fraudulent scenarios. Each transcript embeds adversarial patterns drawn while preserving natural conversational flow. We introduce a hybrid defense that pairs a BERT-based semantic-drift detector (cosine-similarity threshold = 0.70) with a curated keyword and hack-phrase scanner to counter these threats. In aggregate, the system delivered 100 % recall, intercepting every simulated phishing or data-harvesting attempt. The keyword layer achieved perfect precision, generating …

Property Testing Ai: An Efficient Frontier, Paul Sopher Lintilhac

Dartmouth College Ph.D Dissertations

In this dissertation, we take a step towards addressing the major problem of a lack of standardized and rigorous approaches to testing and evaluation of AI systems. Taking inspiration from both the fields of Property Testing and Property Based Testing (for programs), we develop a novel taxonomy of partially overlapping classes of properties of AI systems, including simple properties, compound properties, higher order properties, data relation properties, and architecture-utility properties. We argue that this taxonomy categorizes a diverse set of AI traits -- including accuracy, fairness, robustness, monotonicity, point-wise and global privacy properties, sensitivity, and more -- according to the …

Efficient Gan-Based Adversarial Example Generation Against Ml-Based Network Intrusion Detection Systems, Darren D. Hartono

Master's Theses

In the realm of network security, Network Intrusion Detection Systems (NIDS) are essential for identifying and mitigating malicious activities targeting networked devices. Traditionally, these systems have relied on signature-based and anomaly-based detection techniques. However, the increasing complexity and adapt- ability of cyber threats have driven the adoption of Machine Learning (ML) ap- proaches in modern NIDS, significantly improving their ability to detect a wider range of attack vectors. Despite these advancements, ML-based NIDS remain vulnerable to adversarial examples—deliberately crafted inputs designed to mislead models and trigger incorrect classifications. Originally identified in the field of computer vision, adversarial examples now pose …

Selected Artificial Intelligence Provisions In U.S. Fiscal Year 2025 National Defense Authorization Act, Bert Chapman

Libraries Faculty and Staff Presentations

The 2025 Fiscal Year National Defense Authorization Act contains multiple provisions relating to artificial intelligence (AI). These congressionally mandated provisions direct various sections of the Department of Defense (DOD) and individual U.S. armed service branches to execute congressional intent for AI policymaking. Examples of such intent include identifying and planning DOD's AI workforce, demonstrating AI biotechnology applications for national security, improving the human usability of AI systems, and establishing an AI security center. This presentation will note that reports on these initiatives must be prepared for relevant congressional oversight committees, and, in many cases, are in many cases, publicly released …

Harnessing Neurodiversity And Artificial Intelligence In Education To Bridge The Cybersecurity Workforce Gap, George Antoniou

Faculty and Staff Publications & Presentations

This perspective paper examines how neurodiversity and artificial intelligence (AI) can jointly address the critical workforce shortage in cybersecurity. Drawing on peer-reviewed research, industry reports, and case studies, it explores how neurodivergent individuals—such as those with autism spectrum disorders, ADHD, and dyslexia—possess strengths in pattern recognition, logical reasoning, and attention to detail that align with cybersecurity demands. AI-based educational tools, including adaptive tutoring systems, scenario-based simulations, and real-time analytics, can personalize learning for neurodiverse students, enhancing engagement and skill mastery. The paper discusses how these targeted interventions not only accelerate knowledge retention and practical competence but also foster greater inclusion …

Deepfakes On Trial: Developing A High-Accuracy, Court-Admissible Ai Pipeline For Deepfake Detection In Corporate Fraud Litigation, Aiden J. Green

Honors College Theses

As deepfake technology advances, cybercriminals are increasingly using AI-generated videos and audios to impersonate executives and carry out sophisticated CEO fraud schemes. These synthetic forgeries target human trust and corporate communication systems, creating an urgent need for forensic tools capable of authenticating digital evidence with legal accuracy. This thesis presents a forensic-grade AI deepfake detection pipeline designed for this purpose, emphasizing courtroom admissibility, reproducibility, and evidentiary integrity. Built entirely with free, opensource tools, the framework combines metadata analysis, AI-powered spectrogram analysis, neural artifact detection, and facial manipulation recognition into a transparent workflow that accurately identifies synthetic media. It was trained …

Adversarial Machine Learning: Methods For Attacks And Defenses, Minh Hao Van

Graduate Theses and Dissertations

With the rapid development of machine learning in real-world applications, enhancing security plays an important role. Adversarial machine learning focuses on understanding malicious actions from attackers and developing defensive techniques against such threats when deploying machine learning systems. An attack can occur in different scenarios, such as poisoning attacks during the training stage and evasion attacks during the testing stage. Although extensive research has explored defense strategies to deal with these harmful attacks, there is a need for further research into areas such as how to counteract malicious attacks with healthy noise or how to train an adaptive defense against …

Improving Image Quality In Electrical Capacitance Tomography Using Otsu Thresholding, Josiah Nombo

Tanzania Journal of Engineering and Technology (TJET)

Electrical Capacitance Tomography (ECT) is an imaging technique used in industrial process monitoring, particularly for monitoring and measuring the composition of multiphase flows. Despite its widespread application, the commonly used Linear Back Projection (LBP) algorithm often produces low-quality images due to its limited ability to handle high permittivity contrasts and nonlinearities. This study investigates the use of Otsu thresholding as a post-processing technique to enhance ECT image quality. By maximizing inter-class variance in the image histogram, Otsu thresholding improves contrast, clarity, and structural definition, enabling more effective segmentation of oil and gas components in multiphase flows. The proposed Otsu-based reconstruction …

"Exploring The Training Data Landscape For Ai Based Threathunting For Protecting Intellectual Property", Manzi Siibo, Christopher Kreider

Cybersecurity Undergraduate Research Showcase

This study provides a comprehensive evaluation of the effectiveness that would result in the integration of AI into traditional threat hunting systems. To do so, 10-15 scholarly articles and data sets were evaluated to see the results of AI and machine learning threat hunting versus traditional systems. With so many proven benefits of this integration, this paper also explores how it impacts the protection of Intellectual property which is some of the most important forms of information that threat hunting systems aim to protect.

Leveraging Benford’S Law And Machine Learning For Financial Fraud Detection, Benjamin R. Fu

Cybersecurity Undergraduate Research Showcase

Financial fraud, particularly credit card fraud, continues to pose substantial challenges to financial institutions due to its increasing frequency and impact on consumer trust. While traditional rule-based methods have provided foundational defenses, their limitations in scalability and adaptability have accelerated the adoption of machine learning (ML) techniques. Concurrently, Benford’s Law—a statistical principle often used in forensic accounting—has demonstrated efficacy in detecting anomalies within naturally occurring numerical datasets. This study explores a hybrid fraud detection approach that integrates Benford’s Law with supervised machine learning algorithms, including Logistic Regression, Random Forest, and k-Nearest Neighbors. Using the publicly available European credit card fraud …

Ceker: A Generalizable Llm Framework For Literature Analysis With A Case Study In Unikernel Security, Alex Wollman, John Hastings

Research & Publications

Literature reviews are a critical component of formulating and justifying new research, but are a manual and often time-consuming process. This research introduces a novel, generalizable approach to literature analysis called CEKER which uses a three-step process to streamline the collection of literature, the extraction of key insights, and the summarized analysis of key trends and gaps. Leveraging Large Language Models (LLMs), this methodology represents a significant shift from traditional manual literature reviews, offering a scalable, flexible, and repeatable approach that can be applied across diverse research domains. A case study on unikernel security illustrates CEKER's ability to generate novel …

Impact Of Data Snooping On Deep Learning Models For Locating Vulnerabilities In Lifted Code, Gary Mccully, John Hastings, Shengjie Xu

Research & Publications

This study examines the impact of data snooping on neural networks used to detect vulnerabilities in lifted code, and builds on previous research that used word2vec and unidirectional and bidirectional transformer-based embeddings. The research specifically focuses on how model performance is affected when embedding models are trained with datasets, which include samples used for neural network training and validation. The results show that introducing data snooping did not significantly alter model performance, suggesting that data snooping had a minimal impact or that samples randomly dropped as part of the methodology contained hidden features critical to achieving optimal performance. In addition, …