EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM Copilot for Privacy-Respecting Cyber Incident Response

Pramod Prakash

International Journal of Intelligent Systems and Data Science · 22.08.2026 · 1 (4)

DOI: 10.67231/6s96yv20 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems and Data Science, online erschienen am 22.08.2026. Verfasst von Pramod Prakash. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Security operations centers face challenges in managing complex cyber incidents while protecting sensitive forensic data. This paper introduces a multi-agent LLM framework for automating incident response through collaborative planning, execution, analysis, and reflection. We develop a benchmark comprising 130 subtasks across 12 cyber-range scenarios mapped to NIST Incident Response stages (Detection, Response, Recovery), with ten difficulty levels. The system is evaluated using six LLM variants (GPT-4, GPT-4o, Claude-3.5-Sonnet, Llama3-70B, DeepSeek-V3, and GPT-o1). Results demonstrate that the multi-agent architecture achieves sub-task completion rates of 72.3--86.9%, outperforming baselines by 13.9--21.5 percentage points, with privacy leakage reduced from 16.7% to 3.3%. Failure analysis reveals strategic formulation errors account for 44% of failures, followed by command generation (19%) and evidence omission (18%).

Zitieren

APA

Prakash, P. (2026). LLM Copilot for Privacy-Respecting Cyber Incident Response. International Journal of Intelligent Systems and Data Science, 1(4). https://doi.org/10.67231/6s96yv20

Vancouver

Prakash P. LLM Copilot for Privacy-Respecting Cyber Incident Response. International Journal of Intelligent Systems and Data Science. 2026;1(4). doi:10.67231/6s96yv20

BibTeX
@article{Prakash2026,
  author = {Prakash, Pramod},
  title = {LLM Copilot for Privacy-Respecting Cyber Incident Response},
  journal = {International Journal of Intelligent Systems and Data Science},
  year = {2026},
  volume = {1},
  number = {4},
  doi = {10.67231/6s96yv20}
}
Kostenlos starten →