<![CDATA[Distributed Denial of Service (DDoS) attacks are a major concern in today's linked world because they can compromise the availability and security of networks. We offer a new method for detecting DDoS attacks in real-time by utilising machine learning, more especially the Random Forest algorithm, to counter this threat. Our solution is designed to be easily integrated into web settings using the widely used Streamlit framework. It offers users a user-friendly and interactive platform to keep an eye out for and deal with any risks. Our first step is to compile a large dataset that includes characteristics of network traffic that have been retrieved from both legitimate and malicious sources. The data is prepared for training and evaluation through feature engineering and careful preparation. We build a prediction model that can distinguish between typical traffic patterns and abnormal ones that indicate DDoS attacks using the Random Forest algorithm, which is known for being robust and scalable. To prove its effectiveness in identifying and categorising DDoS attacks with little false positives, the created model is subjected to thorough testing using well-established performance measures. In addition, we improve the model's accessibility and usability by integrating it easily into a web application that is built on Streamlit. With the model displaying great accuracy and efficiency in real-time circumstances, our testing results demonstrate promising detecting capabilities. In ever-changing web environments, our solution helps to strengthen network resilience and protects against disruptive cyber threats by giving stakeholders proactive DDoS mitigation capabilities.]]>
