Cyber-security has recently resulted in significant changes in operations and technology, and data science is also developing in the context of computing. It is crucial to draw patterns or insights about security incidents from cyber-security data and create models based on the essential data in order to automate and make security systems useful. Security issues increase along with increased internet usage. Due to system security problems, malware degrades system performance and affects data privacy. Attacks can be detected and reported using intrusion detection systems (IDS). It is determined by an Intrusion Detection System (IDS) whether network traffic behaviour is typical, unusual, or suggestive of a specific type of attack. Machine Learning is being used more and more in cyber security. Making the process of detecting malware more realistic, scalable, and efficient than current methodologies is the main objective of applying Machine Learning to cyber security. As a result, Machine Learning-based intrusion system security against threats is presented in this study. This system uses the Support Vector Machine (SVM) classifier to detect threats in a highly accurate and efficient manner. Accuracy, sensitivity, and specificity will be used as metrics to assess the performance of the system being presented.