AUTOMATED CYBERSECURITY INCIDENT RESPONSE: A REINFORCEMENT LEARNING APPROACH
AI and Data Science Journal · 2025
DOI: 10.61784/adsj3010 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI and Data Science Journal, 2025. Verfasst von MingJie Zhao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cybersecurity incident response is critical for defending digital infrastructures from evolving cyber threats. Traditional manual systems and rule-based automation methods cannot efficiently cope with dynamic and sophisticated attacks. This paper explores the application of reinforcement learning (RL) to automate cybersecurity incident response. By modeling the response process as an RL problem, where an agent learns from interactions with the environment, the proposed system aims to enhance detection accuracy, minimize response times, and reduce false positives. Experimental results demonstrate the system's ability to mitigate threats effectively, showing that RL can significantly improve the efficiency and scalability of cybersecurity defenses. This approach leverages machine learning to automate decisions in real-time, adapting to evolving threats and optimizing incident response strategies. The integration of RL in incident response has the potential to dramatically reduce human error, improve system adaptability, and scale efficiently in complex, high-volume environments.
Zitieren
APA
Zhao, M., & Chen, R. (2025). AUTOMATED CYBERSECURITY INCIDENT RESPONSE: A REINFORCEMENT LEARNING APPROACH. AI and Data Science Journal. https://doi.org/10.61784/adsj3010
Vancouver
Zhao M, Chen R. AUTOMATED CYBERSECURITY INCIDENT RESPONSE: A REINFORCEMENT LEARNING APPROACH. AI and Data Science Journal. 2025. doi:10.61784/adsj3010
BibTeX
@article{Zhao2025,
author = {Zhao, MingJie and Chen, Rui},
title = {AUTOMATED CYBERSECURITY INCIDENT RESPONSE: A REINFORCEMENT LEARNING APPROACH},
journal = {AI and Data Science Journal},
year = {2025},
doi = {10.61784/adsj3010}
}
EUVIMED