EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning in Cybersecurity: Enhancing Threat Detection and Response

Imran Shahzad

Computer Science Bulletin · 31.12.2025 · 8 (02) · 598-614

DOI: 10.71465/csb187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Science Bulletin, online erschienen am 31.12.2025. Verfasst von Imran Shahzad. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cybersecurity threats are becoming more sophisticated and pervasive, presenting significant challenges to organizations globally. In response to these evolving threats, Machine Learning (ML) technologies have emerged as a powerful tool to enhance threat detection and response mechanisms. This paper explores the role of Machine Learning in modern cybersecurity systems, focusing on how it can improve the identification, classification, and mitigation of cyber threats. We provide an in-depth review of various ML algorithms used in cybersecurity, their effectiveness in detecting novel attack patterns, and the impact of ML on improving response time to incidents. Additionally, the paper highlights the integration of ML with existing security frameworks, challenges in implementation, and the future potential of ML in cybersecurity. We conclude by emphasizing the need for continuous advancement in ML techniques to adapt to increasingly complex cybersecurity threats

Zitieren

APA

Shahzad, I. (2025). Machine Learning in Cybersecurity: Enhancing Threat Detection and Response. Computer Science Bulletin, 8(02), 598-614. https://doi.org/10.71465/csb187

Vancouver

Shahzad I. Machine Learning in Cybersecurity: Enhancing Threat Detection and Response. Computer Science Bulletin. 2025;8(02):598-614. doi:10.71465/csb187

BibTeX
@article{Shahzad2025,
  author = {Shahzad, Imran},
  title = {Machine Learning in Cybersecurity: Enhancing Threat Detection and Response},
  journal = {Computer Science Bulletin},
  year = {2025},
  volume = {8},
  number = {02},
  pages = {598--614},
  doi = {10.71465/csb187}
}
Kostenlos starten →