XGBOOST–POWERED PROACTIVE FIREWALL: AN ENSEMBLE LEARNING FRAMEWORK FOR NETWORK THREAT DETECTION AND PREVENTION.

Saved in:

Bibliographic Details
Title:	XGBOOST–POWERED PROACTIVE FIREWALL: AN ENSEMBLE LEARNING FRAMEWORK FOR NETWORK THREAT DETECTION AND PREVENTION.
Authors:	PENDHARI, Nazneen¹, ANSARI, Belal¹, AHMAD, Azaz¹, SHAIKH, Farhan¹, SHAIKH, Mohammad Saad¹
Source:	Acta Technica Corviniensis - Bulletin of Engineering. Apr-Jun2025, Vol. 18 Issue 2, p25-32. 8p.
Subjects:	Ensemble learning, Firewalls (Computer security), Anomaly detection (Computer security), Internet security, Feature selection
Abstract:	With the rapid advancement of digital technologies, cyber threats are becoming more sophisticated, targeting network vulnerabilities and causing significant disruptions. Conventional firewalls and signature–based intrusion detection systems often fail to detect new and evolving attack patterns, leading to high false positives, delayed responses, and security breaches. These threats result in substantial financial losses, service downtime, data theft, and reputational damage, posing a critical challenge for organizations. This research proposes an XGBoost–powered proactive firewall to mitigate these risks, utilizing ensemble learning techniques for real–time threat detection and adaptive network security. The system enhances detection accuracy by analyzing network traffic and identifying malicious behavior patterns while reducing false alarms. The approach incorporates feature selection, anomaly detection, and decision fusion to strengthen cybersecurity defenses. Experimental evaluations on standard intrusion detection datasets demonstrate that the proposed model effectively improves threat detection capabilities, offering a robust solution for modern network security challenges. [ABSTRACT FROM AUTHOR]
	Copyright of Acta Technica Corviniensis - Bulletin of Engineering is the property of University Politehnica Timisoara, Faculty of Engineering Hunedoara and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	With the rapid advancement of digital technologies, cyber threats are becoming more sophisticated, targeting network vulnerabilities and causing significant disruptions. Conventional firewalls and signature–based intrusion detection systems often fail to detect new and evolving attack patterns, leading to high false positives, delayed responses, and security breaches. These threats result in substantial financial losses, service downtime, data theft, and reputational damage, posing a critical challenge for organizations. This research proposes an XGBoost–powered proactive firewall to mitigate these risks, utilizing ensemble learning techniques for real–time threat detection and adaptive network security. The system enhances detection accuracy by analyzing network traffic and identifying malicious behavior patterns while reducing false alarms. The approach incorporates feature selection, anomaly detection, and decision fusion to strengthen cybersecurity defenses. Experimental evaluations on standard intrusion detection datasets demonstrate that the proposed model effectively improves threat detection capabilities, offering a robust solution for modern network security challenges. [ABSTRACT FROM AUTHOR]
ISSN:	20673809