Abstract:

With the exponential growth of cyber threats, robust intrusion detection systems (IDS) are critical for safeguarding digital infrastructures. This paper presents CyberGuard AI, a multi-model intrusion detection framework leveraging Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM) algorithms to enhance detection accuracy and minimize false positives. By integrating these machine learning models, CyberGuard AI effectively identifies anomalies and malicious activities across network traffic data. Experimental results demonstrate a high detection rate and superior performance compared to single-model approaches, providing a scalable and reliable solution for contemporary cybersecurity challenges.

Description:

.