Year: 2025
Type: article
Abstract: The growing dependence on interconnected digital systems has resulted in a significant rise in complex and intelligent cyber threats that challenge the effectiveness of conventional security mechanisms. Traditional intrusion detection approaches, which rely on static rules and predefined signatures, often fail to detect newly emerging and adaptive attacks in real time. To overcome these limitations, this paper presents an artificial intelligence–based cybersecurity threat monitoring and response system capable of identifying and mitigating malicious network activities automatically. The proposed framework continuously observes network traffic and evaluates critical attributes such as protocol usage, packet behavior, and traffic flow patterns using supervised machine learning models, including Random Forest and K-Nearest Neighbors. To assess system performance under realistic conditions, an attacker simulation module is integrated to generate controlled attack scenarios. When suspicious activity is detected, the system initiates automated firewall recovery actions and immediately notifies administrators through real-time alerts. The experimental implementation demonstrates improved detection accuracy, faster response time, and enhanced network security, making the proposed system suitable for modern dynamic network environments.
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7117756819
FWCI:
Cites:
Cited by:
Related to: