EUVIMEDEUVIMED entdecken
Crossref

Machine Learning and Deep Learning-Based Intrusion Detection for Cybersecurity

Sudhakara Reddy Peram

Journal of AI-Driven Cybersecurity Systems · 2026 · 1 (1) · 1-8

DOI: 10.55124/jaic.v1i1.104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of AI-Driven Cybersecurity Systems, 2026. Verfasst von Sudhakara Reddy Peram.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study unequivocally demonstrates how machine learning algorithms may increase the accuracy of intrusion detection. Research Importance: Cyber security threats are on the rise, and as such, intrusion detection systems need to be more intelligent to detect potential cyber threats. The prediction of packet rates helps to improve intrusion detection accuracy, thus improving the reliability, scalability, and reliability of network security. Methodology: The paper makes use of various methodologies to improve intrusion detection accuracy by applying machine learning algorithms to predict packet rates. The paper makes use of statistical analysis to understand the relationships between variables. Input Parameters (Alternative): The study has also included other input parameters such as connection duration, failed login attempts, and intrusion detected. Here, connection duration refers to the time spent on session activities, failed login attempts may indicate unauthorized access, and intrusion detected may indicate malicious activities. These input parameters are significant in identifying patterns related to network anomalies and security issues. Evaluation Parameter (Output Parameter: Packet Rate): Changes in the packet rate may indicate abnormal activities such as intrusions and inefficiencies. Accurate prediction of the packet rate is significant in monitoring network activities and potential intrusions. Results: The results obtained from the experiment indicate that the Linear Regression and AdaBoost Regression models can be used to predict the packet rate with moderate accuracy. However, the AdaBoost Regression model can be considered more accurate than the linear regression model in terms of error reduction and prediction accuracy. The experiment's findings indicate that machine learning models are useful for forecasting network packet rates and for creating intrusion detection systems. Among the models taken into account for the experiment, the AdaBoost Regression model can be considered more accurate than the Linear Regression model. Keywords: Cybersecurity, Machine Learning, Intrusion Detection System, Packet Rate Prediction.

Zitieren

APA

Peram, S. R. (2026). Machine Learning and Deep Learning-Based Intrusion Detection for Cybersecurity. Journal of AI-Driven Cybersecurity Systems, 1(1), 1-8. https://doi.org/10.55124/jaic.v1i1.104

Vancouver

Peram SR. Machine Learning and Deep Learning-Based Intrusion Detection for Cybersecurity. Journal of AI-Driven Cybersecurity Systems. 2026;1(1):1-8. doi:10.55124/jaic.v1i1.104

BibTeX
@article{Peram2026,
  author = {Peram, Sudhakara Reddy},
  title = {Machine Learning and Deep Learning-Based Intrusion Detection for Cybersecurity},
  journal = {Journal of AI-Driven Cybersecurity Systems},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {1--8},
  doi = {10.55124/jaic.v1i1.104}
}
Kostenlos starten →