Cyberally: Leveraging LLMS and knowledge graphs to empower cyber defenders
Author Identifier
Ahmad Mohsin: https://orcid.org/0000-0001-9023-0851
Ahmed Ibrahim: https://orcid.org/0000-0002-4760-3533
Helge Janicke: https://orcid.org/0000-0002-1345-2829
Document Type
Conference Proceeding
Publication Title
WWW Companion 2025 Companion Proceedings of the ACM Web Conference 2025
First Page
2851
Last Page
2854
Publisher
Association for Computing Machinery
School
School of Science
RAS ID
82132
Funders
Cyber Security Research Centre Limited
Abstract
The increasing frequency and sophistication of cyberattacks demand innovative approaches to strengthen defense capabilities. Training on live infrastructure poses significant risks to organizations, making secure, isolated cyber ranges an essential tool for conducting Red vs. Blue Team training events. These events enable security teams to refine their skills without impacting operational environments. While such training provides a strong foundation, the ever-evolving nature of cyber threats necessitates additional support for effective defense. To address this challenge, we introduce CyberAlly, a knowledge graph-enhanced AI assistant designed to enhance the efficiency and effectiveness of Blue Teams during incident response. Integrated into our cyber range alongside an open-source SIEM platform, CyberAlly monitors alerts, tracks Blue Team actions, and suggests tailored mitigation recommendations based on insights from prior Red vs. Blue Team exercises. This demonstration highlights the feasibility and impact of CyberAlly in augmenting incident response and equipping defenders to tackle evolving threats with greater precision and confidence.
DOI
10.1145/3701716.3715171
Access Rights
free_to_read
Comments
Kim, M., Wang, J., Moore, K., Goel, D., Wang, D., Mohsin, A., Ibrahim, A., Doss, R., Camtepe, S., & Janicke, H. (2025). Cyberally: Leveraging LLMS and knowledge graphs to empower cyber defenders. Companion Proceedings of the ACM on Web Conference 2025, 2851-2854. https://doi.org/10.1145/3701716.3715171