Publications

@inproceedings{ahmed_abstract_2025,

title = {From Abstract Prompts to Cybersecurity Labs: Automating Virtual Environment Design and Deployment with Multi-Agent Systems and LLM-Driven Orchestration},

author = {Y. Ahmed and A. Eissa and O. Harb and O. Miniesy and Z. Miniesy and M. Noureldin and A. E. Mougy},

editor = {M. Alsmirat and F. Alkhabbas and M. Al-Abdullah and Y. Jararweh},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105016685428&doi=10.1109%2FICSC65596.2025.11140357&partnerID=40&md5=053515e92d70c5c694cc8ba888f39afa},

doi = {10.1109/ICSC65596.2025.11140357},

isbn = {9798350392920 (ISBN)},

year  = {2025},

date = {2025-01-01},

pages = {99–107},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Cyber ranges are essential for cybersecurity training, but current systems face challenges like resource-intensive infrastructures, static configurations, and laborious setups, limiting scalability and accessibility, especially for educational institutions with fewer resources. To address these issues, this paper introduces a containerized multi-agent system that automates the design and deployment of cybersecurity training environments. Using large language models (LLMs) for scenario orchestration, the system transforms natural language prompts into fully functional environments through Docker containerization. It features three specialized agents: a master agent for scenario planning, machine worker agents for environment and vulnerability generation, and a quality assurance agent for validation and debugging, ensuring modularity, scalability, and precision. Evaluated across 14 diverse attack scenarios, the system demonstrates high accuracy in generating web vulnerabilities, network exploits, and multi-step attacks. By automating scenario creation and deployment, this system enhances cybersecurity education and training, bridging critical gaps and offering a scalable, adaptive, and resource-efficient solution to meet the growing demand for skilled cybersecurity professionals. © 2025 Elsevier B.V., All rights reserved.},

keywords = {Automated scenario generation, Containerization, Containers, Cybe range, cyber ranges, Cyber security, Cybersecurity, Cybersecurity training, Docker, Environment generation cybe range lab generation, environment generation cyber range lab generation, Intelligent Agents, Language Model, Large language model, large language models (LLMs), Multi agent systems, Multi-agent systems, Multiagent systems (MASs), Network Security, Personnel training, Quality assurance, Scalability, Scenarios generation, Virtual Reality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{jacoby_efficient_2023,

title = {Efficient Cloud Pipelines for Neural Radiance Fields},

author = {D. Jacoby and D. Xu and W. Ribas and M. Xu and T. Liu and V. Jeyaraman and M. Wei and E. D. Blois and Y. Coady},

editor = {S. Chakrabarti and R. Paul},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85179765347&doi=10.1109%2FUEMCON59035.2023.10316126&partnerID=40&md5=cb75c3398a28ac80a8bc8f35da278d50},

doi = {10.1109/UEMCON59035.2023.10316126},

isbn = {9798350304138 (ISBN)},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE Annu. Ubiquitous Comput., Electron. Mob. Commun. Conf., UEMCON},

pages = {114–119},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Since their introduction in 2020, Neural Radiance Fields (NeRFs) have taken the computer vision community by storm. They provide a multi-view representation of a scene or object that is ideal for eXtended Reality (XR) applications and for creative endeavors such as virtual production, as well as change detection operations in geospatial analytics. The computational cost of these generative AI models is quite high, however, and the construction of cloud pipelines to generate NeRFs is neccesary to realize their potential in client applications. In this paper, we present pipelines on a high performance academic computing cluster and compare it with a pipeline implemented on Microsoft Azure. Along the way, we describe some uses of NeRFs in enabling novel user interaction scenarios. © 2023 Elsevier B.V., All rights reserved.},

keywords = {Azure, Change detection, Cloud analytics, Cloud computing, Cloud-computing, Cluster computing, Containerization, Creatives, Geo-spatial, Multi-views, Neural radiance field, Neural Radiance Fields, Pipelines, User interfaces, Virtual production, Vision communities, Windows operating system},

pubstate = {published},

tppubtype = {inproceedings}

}