The great majority of programs on the online platform have made it clear that both the amount of data collected and the number of users have increased significantly. Due to the difficulty in efficiently analyzing and processing such a massive volume of data, big data techniques and cloud platforms have been developed. Additionally, this raises the frequency of DoS assaults against the networks and data storage platforms that underpin these big systems. DoS attacks have the power to take down systems and stop authorized users from using the services. Since it raises several security issues for users, unauthorized access is also very harmful to the strategy. Therefore, the goal of this paper is to offer a better solution to this issue by utilizing machine learning techniques that can precisely identify network incursions for Denial-of-Service assaults. To produce a highly accurate intrusion detection system, the suggested methodology makes use of fuzzy ANN on the KDD dataset in conjunction with K means clustering. The method’s advantage over various earlier approaches to intrusion detection to gauge the model’s accuracy in a restricted setting has been demonstrated by rigorous testing.