The purpose of this study was to examine the browsing habits of web searchers and how attacks could be avoided. Many solution-based solutions developed to counter Distributed Denial of Service (DDoS) attacks focus on the Transmission Control Protocol and Internet Protocol layers rather than the higher layer. To characterise the browsing habits of web searchers, an extended hidden semi-Markov model is developed. In order to reduce the computational amount introduced by the model’s huge state space, a forward method based on the M-algorithm is created for the online implementation of the model. To determine the user’s normalcy, the entropy of the user’s HTTP request sequence that is accurate to the replica is employed as a criterion. Finally, experiments are carried out to confirm the accuracy of our model and algorithm. For anomaly detection, a novel on-line algorithm based on the M-algorithm was developed. To validate our model, we analysed real traffic data from an educational website as well as created App-DDoS attack traffic.
S. S. Sreeja Mole
Department of ECE, Government College of Engineering, Tirunelveli, India.
Department of ECE, ACETECH, Karaikudi, India.
View Book:- https://stm.bookpi.org/NVST-V8/article/view/4841