DDoS Risk Assesment using Machine Learning Techniques

The result of exploiting holes in safeguarding Internet of Things (IoT) devices, the amount of cyber-attacks and data breaches has skyrocketed across various corporations, companies, and sectors. Because its capacity to extract and learn deep characteristics of known assaults and detect novel attacks without the need for manual feature engineering, machine learning is used in cyber-attack detection. Despite the use of improved Machine Learning (ML) techniques for intrusion detection, the assault remains a huge danger to the Internet. The primary target of this research is to identify and detect assaults on the network. The expansion of social networks is now increasing on a daily basis. However, detecting the assaults is a difficult task. By examining the information in the KDDCUP Dataset, this project will dynamically detect the attack. The method of feature scaling is employed to standardize a range of independent variables or data constituents. The feature reduction PCA technique is used to locate the directions of highest variance in high-dimensional data and project it onto a new subspace with the same or less dimensions than the original one. Finally, the ML classification technique is used to categorise the data. Based on the assaults and the typical event, the final report is created..