24067 research outputs found
Sort by
Examining the Capabilities of GhidraMCP and Claude LLM for Reverse Engineering Malware
No full textCan Large Language Models (LLMs) enhance the efficiency of reverse engineering by assisting malware analysts in the de-obfuscation of ransomware and other forms of malicious software? This research explores the integration of LLMs into reverse engineering workflows through the use of GhidraMCP, a plugin designed for the Ghidra open-source software reverse engineering suite. GhidraMCP leverages the capabilities of Claude’s Sonnet 4 model (as well as other LLMs) to rename decompiled variables and functions, generate descriptive annotations for disassembled code, and highlight potentially relevant strings or routines. These features are intended to reduce the cognitive load on analysts and accelerate the identification of critical components such as encryption routines, embedded URLs, command-and-control (C2) indicators, and external library calls within malware samples.
This study compares traditional reverse engineering workflows with LLM-augmented workflows using GhidraMCP. Multiple pseudo-ransomware samples were analyzed to assess differences in discovery efficiency, accuracy of function labeling, and qualitative analytical quality. Although no formal timing metrics were recorded, the research team determined that the LLM-augmented process consistently achieved insights more quickly and with fewer manual steps. In several instances, Claude Sonnet 4 successfully identified static relationships and artifacts that human analysts initially overlooked, demonstrating its potential to enhance traditional workflows through contextual inference and advanced pattern recognition.
The combination of GhidraMCP and Claude Sonnet 4 effectively leveraged static analysis to identify the hidden flags for ESCALATE challenges one through seven. However, while the research team was ultimately able to solve all challenges, several required dynamic analysis and binary patching—tasks that the current LLM-augmented setup could not perform due to the lack of patching capabilities within GhidraMCP. It remains unclear whether this limitation stems from Ghidra, the plugin, or the integration framework itself. During testing, Claude Sonnet 4 occasionally exhibited hallucinations, producing inaccurate or speculative annotations that required human correction and additional prompting, particularly during challenges three and four. These occurrences emphasize the ongoing need for human oversight and iterative validation when employing generative AI in critical cybersecurity tasks.
Despite these limitations, the findings indicate that LLM-augmented reverse engineering can meaningfully improve analytical comprehension, efficiency, and context awareness. Claude Sonnet 4’s linguistic reasoning and ability to infer code intent proved especially valuable for de-obfuscating complex binaries. Future work will focus on enabling dynamic capabilities within GhidraMCP to support patching and execution-based testing, as well as refining prompt strategies and hallucination detection. This research establishes a foundation for the continued development of intelligent, LLM-assisted tooling designed to augment human expertise in malware analysis and reverse engineering
Systematic Review of Elementary Cybersecurity Education: Curriculum, Pedagogy, and Barriers
Get PDFAbstract -As children increasingly engage with digital platforms, the need for effective cybersecurity education has become urgent. This systematic review synthesizes 81 studies published between 2017 and 2024 to examine global curricula research focus and topics, pedagogical approaches and assessment methods, and key challenges in elementary cybersecurity education. The findings reveal six major thematic categories: student awareness, parental mediation, teacher engagement, curriculum design, community and policy support, and pedagogical innovation. Among instructional strategies, game-based learning and narrative storytelling emerge as the most frequently explored. Despite this growth, major gaps remain in curriculum consistency, teacher preparation, assessment rigor, and stakeholder coordination. By applying Bronfenbrenner’s ecological systems theory in both coding and result interpretation, this review offers a systems-level perspective that highlights the interconnected roles of students, families, educators, institutions, and policymakers. The study contributes a synthesis of global research and provides actionable insights for designing developmentally appropriate, scalable, and context-responsive cybersecurity education programs in elementary settings
Black Men and Health Literacy: Strategies for Improvement in a Digital Age Through the Adaptation of a Chronic Disease Self-Management Program
Get PDFHealth literacy is a critical determinant of health outcomes, yet it is often overlooked, particularly among marginalized groups. This paper explores the significance of health literacy, with a particular focus on low-income African American and Black (AA/B) men, a population that faces unique challenges due to intersecting factors such as race, gender, socioeconomic status, and educational disparities. We examine how these factors contribute to health literacy gaps, highlighting adverse effects on health outcomes for AA/B men compared to the general population. Additionally, we stress the growing importance of digital literacy in an increasingly technology-driven world. Not actively addressing digital health literacy, especially within chronic disease self-management programs (CDSMPs), further exacerbates health disparities within this group. Recommendations are provided for improving health literacy, with specific strategies to also enhance general literacy and digital literacy, among low-income AA/B men. The paper also advocates for a systematic review of the existing literature on health literacy among this group, emphasizing the need for tailored interventions that account for the unique challenges faced by low-income AA/B men. In conclusion, the paper underscores the critical need for targeted research and practical approaches to improve health literacy and ultimately health outcomes for AA/B men in the digital age, particularly through CDSMPs
Book Review: Georgia\u27s Historical Recipes: Seeking Our State\u27s Oldest Written Foodways and the Stories Behind Them
Get PDFSymphony Orchestra
Get PDFNathaniel F. Parker, Director & Conductorhttps://digitalcommons.kennesaw.edu/musicprograms/2951/thumbnail.jp
UC-1262 Georgia Watch - Georgia Hospital Accountability Score
No full textGeorgia Watch and the members of this team have partnered to change how Georgia residents understand their healthcare by providing a source of objective metrics which affect their care. This project represents the quintessential React Project produced with the purpose of a reactive interface for the end user, built for maintainability for any subsequent developers. The hospital data is maintained in JSON format for its ease of parsing and adjustment pending any changes. The interactive map was developed through the MAPBOX library, and the team is maintaining a deployment via an independent repository with necessary control over the website
GRP-1265 Optimizing CPU Scheduling for Deep Learning and LLM Inference Using ONNX Runtime
No full textModern applications rely on AI models that must perform real-time predictions on resource-constrained edge devices like laptops. The default OS scheduler often increases context switching, which slows down deep learning and LLM inference. Since these models depend heavily on parallel processing, efficient CPU scheduling becomes essential. In this project, we analyzed how core pinning and thread-level parallelism improve inference performance on a Windows system. Using multiple micro-batch sizes. We compare latency, throughput, and per-sample inference time. The goal is to show how simple OS-level optimization can significantly improve real-time performance for both deep learning models and LLM
GRP-1190 Hybrid Virtualization Performance Modeling Using Monte Carlo Simulation
No full textThis project presents a performance analysis of virtualization, containerization, and hybrid container-in-VM architectures in modern operating systems. Virtual machines provide strong isolation and system stability but incur higher CPU, memory, and startup costs. Containers offer lightweight and fast execution but rely on weaker isolation. To evaluate a balanced alternative, performance data was extracted from recent research and modeled using a Monte Carlo simulation with 1,000 randomized workloads. A unified Hybrid Efficiency Score (HES) was introduced to compare systems consistently, weighting efficiency at 70% and isolation at 30%. Simulation results demonstrate that hybrid systems achieve the highest efficiency–isolation balance, with an average HES of ~0.82, compared to containers (~0.78) and virtual machines (~0.62). Hybrid architectures significantly reduce CPU overhead to 14.86%, nearly one-third lower than VMs (29.91%), and provide better energy savings (31.84%) than both VMs (0%) and containers (24.94%). Startup time also remains moderate (3.01 s), bridging the gap between fast containers (1.04 s) and slow VMs (30.19 s). Overall, these findings highlight hybrid container-in-VM architectures as a promising approach for achieving better trade-offs in efficiency, isolation, and scalability across cloud, edge, and high-performance computing environments