EUVIMEDEUVIMED entdecken
Crossref

Real-Time Pattern Solution Cybersecurity Threat Detection in a Mode Computer Network Environment

Mehdi Karimi, Saad Khalaf

BigDataStream Mining · 30.06.2025 · 1 (2) · 61

DOI: 10.70023/sahd/b125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BigDataStream Mining, online erschienen am 30.06.2025. Verfasst von Mehdi Karimi und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a result of the use of polymorphic attack tactics, newly discovered vulnerabilities, and potent malware, the vulnerabilities of modern computer networks are far higher than they have ever been. Traditional cybersecurity systems often struggle with scalability and high false-positive rates. This is mostly due to the fact that they use reactive analytics, stringent rule sets, and lengthy detection times. This gap demonstrates the importance of threat detection systems that can respond to changing network activity, learn from mistakes, and capitalize on trends in real time. It also highlights the importance of providing such systems. Based on the combination of Adaptive Pattern-Based Detection (APBD) and Machine-Driven Threat Classification (MDTC), the proposed Real-Time Pattern Solution (RTPS) can address these concerns. This is accomplished by simplifying the analytical architecture of the existing network infrastructure, which is the result. RSC, APL, and Real-Time Rule Filtering are components of this hybrid RT-ML framework, which this technique uses to maintain continuous surveillance of network traffic. This framework is used to maintain network traffic surveillance. APBD uses temporal-spatial behavioral signals to discern when things aren't quite right. On the other hand, MDTC uses lightweight machine learning models that are effective in situations with relatively short durations, thanks to their ease of use. By using the Real-Time Pipeline System (RTPS), you can monitor events in real time, identify potential threats early, and perform risk assessments automatically with a delay of less than 1 millisecond. The effectiveness of the system has been demonstrated to have greatly improved as a result of experiments conducted on corporate networks using a wide range of data types. Since real-time intrusion prevention systems (RTPS) improve detection accuracy, reduce false alarms, and speed up response time, traditional intrusion detection systems are inferior to RTPS. This is because RTPS can improve detection accuracy. This technology is ideal for the next generation of cybersecurity ecosystems, as it can be easily adapted to a wide range of situations. This makes it an ideal candidate for the future. All of the following are covered in this category: cloud-based systems, encrypted traffic flows, and data streams that contain a significant number of nodes distributed across different locations. RTPS is an intelligent cybersecurity solution that can be used in a variety of scenarios, which is the final point to mention from here forward. Even in the most complex network settings, it can make it easier to spot possible threats in real time. This is a significant advantage. This technology has the potential to build digital infrastructure that is not only dependable but also long-lasting. This goal can be achieved by combining quick classification algorithms with adaptive pattern learning. Over the present concerns over the insecurity of cyberspace, this does a reasonably great job of addressing those concerns.

Zitieren

APA

Karimi, M., & Khalaf, S. (2025). Real-Time Pattern Solution Cybersecurity Threat Detection in a Mode Computer Network Environment. BigDataStream Mining, 1(2), 61. https://doi.org/10.70023/sahd/b125

Vancouver

Karimi M, Khalaf S. Real-Time Pattern Solution Cybersecurity Threat Detection in a Mode Computer Network Environment. BigDataStream Mining. 2025;1(2):61. doi:10.70023/sahd/b125

BibTeX
@article{Karimi2025,
  author = {Karimi, Mehdi and Khalaf, Saad},
  title = {Real-Time Pattern Solution Cybersecurity Threat Detection in a Mode Computer Network Environment},
  journal = {BigDataStream Mining},
  year = {2025},
  volume = {1},
  number = {2},
  pages = {61},
  doi = {10.70023/sahd/b125}
}
Kostenlos starten →