The use of machine learning algorithms has become essential in the cybersecurity industry. The increasing frequency of government intrusions and malicious actions has made the necessity for strong defenses and protective measures vital. Designing an automated and efficient digital threat detection mechanism is one of the most difficult tasks in network security. This study proposes a cyber-event detection model that effectively forecast cyber-occurrences to resolve this issue. As a result, a hybrid machine learning model using support vector machines (SVM) with random forest (RF) is proposed. The proposed algorithm is termed HS-RF. By identifying and thwarting harmful attacks, the hybrid solution that has been proposed contributes to improving the system’s overall security. Machine learning models utilize complex algorithms to sift through mountains of data, identify suspicious patterns, and take preventative measures against security breaches. As a consequence, detection rates are increased and false-positive rates are decreased, which makes the defense against cyberattacks more effective. The idea might potentially be applied to the development of unique corporate security architectures.
Ashwag Albakri (Sat,) studied this question.